{"data":[{"id":"academy-guide","name":"Claude Academy Guide","tagline":"Claude Academy course matcher for product questions","when":"Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: \"how do I\", \"how can I\", \"getting started with\", \"what can Claude do\", \"teach me\", \"learn to use\"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/academy-guide/SKILL.md","catch":"Anthropic product skill. Recommends academy.claude.com courses — never invent them. Idle when the user wants the task done, not a tutorial.","links":{"self":"/api/skills/academy-guide","html":"/skills/academy-guide","markdown":"/skills/academy-guide.md"}},{"id":"algorithmic-art","name":"Algorithmic Art","tagline":"Seeded p5.js generative-art skill","when":"Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/algorithmic-art/SKILL.md","catch":"Idle unless someone asks for generative art. Original work only; not a copy-an-artist skill.","links":{"self":"/api/skills/algorithmic-art","html":"/skills/algorithmic-art","markdown":"/skills/algorithmic-art.md"}},{"id":"brand-guidelines","name":"Anthropic Brand Guidelines","tagline":"Anthropic brand colors and type for artifacts","when":"Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/brand-guidelines/SKILL.md","catch":"This is Anthropic's look — Poppins, Lora, #d97757 — not “your brand.”","links":{"self":"/api/skills/brand-guidelines","html":"/skills/brand-guidelines","markdown":"/skills/brand-guidelines.md"}},{"id":"canvas-design","name":"Canvas Design","tagline":"Poster and static visual design in PNG/PDF","when":"Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/canvas-design/SKILL.md","catch":"Static PNG/PDF posters. Not product UI. Will sit idle unless someone asks for a piece.","links":{"self":"/api/skills/canvas-design","html":"/skills/canvas-design","markdown":"/skills/canvas-design.md"}},{"id":"claude-api","name":"Claude API","tagline":"Claude API / Anthropic SDK reference before you guess","when":"- Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/claude-api/SKILL.md","catch":"Vendor + broad-trigger Catch: fires on almost any LLM-shaped task and steers to Anthropic. Skip when another provider is the job.","links":{"self":"/api/skills/claude-api","html":"/skills/claude-api","markdown":"/skills/claude-api.md"}},{"id":"doc-coauthoring","name":"Doc Coauthoring","tagline":"Structured loop for co-authoring specs and docs","when":"Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/doc-coauthoring/SKILL.md","catch":"Anthropic’s three-stage writing loop. Never-fire if the agent just writes the doc. Distinct from Sentry’s copy in getsentry/skills.","links":{"self":"/api/skills/doc-coauthoring","html":"/skills/doc-coauthoring","markdown":"/skills/doc-coauthoring.md"}},{"id":"frontend-design","name":"Frontend Design","tagline":"Intentional visual direction so UI is not template-default","when":"Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/frontend-design/SKILL.md","catch":"Aesthetic direction, not a component library. Idle unless someone is actually choosing a look.","links":{"self":"/api/skills/frontend-design","html":"/skills/frontend-design","markdown":"/skills/frontend-design.md"}},{"id":"mcp-builder","name":"MCP Builder","tagline":"How to build MCP servers in Python or TypeScript","when":"Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/mcp-builder/SKILL.md","catch":"How to *build* an MCP server. Not how to wire one that already exists.","links":{"self":"/api/skills/mcp-builder","html":"/skills/mcp-builder","markdown":"/skills/mcp-builder.md"}},{"id":"skill-creator","name":"Skill Creator","tagline":"Create, edit, eval, and tune agent skills","when":"Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md","catch":"Meta-skill for authoring and eval-ing skills. Idle unless you are writing a skill.","links":{"self":"/api/skills/skill-creator","html":"/skills/skill-creator","markdown":"/skills/skill-creator.md"}},{"id":"slack-gif-creator","name":"Slack GIF Creator","tagline":"Animated GIFs sized and timed for Slack","when":"Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/slack-gif-creator/SKILL.md","catch":"Will sit idle unless someone actually asks for a Slack GIF.","links":{"self":"/api/skills/slack-gif-creator","html":"/skills/slack-gif-creator","markdown":"/skills/slack-gif-creator.md"}},{"id":"theme-factory","name":"Theme Factory","tagline":"Ten preset themes, or a new one, for artifacts","when":"Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/theme-factory/SKILL.md","catch":"Ten palettes for artifacts. Idle unless someone wants a theme applied.","links":{"self":"/api/skills/theme-factory","html":"/skills/theme-factory","markdown":"/skills/theme-factory.md"}},{"id":"web-artifacts-builder","name":"Web Artifacts Builder","tagline":"Multi-component claude.ai HTML artifacts (React + shadcn)","when":"Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/web-artifacts-builder/SKILL.md","catch":"Locked to claude.ai HTML artifacts (React + Tailwind + shadcn bundle). Not a general web app skill.","links":{"self":"/api/skills/web-artifacts-builder","html":"/skills/web-artifacts-builder","markdown":"/skills/web-artifacts-builder.md"}},{"id":"webapp-testing","name":"Webapp Testing","tagline":"Playwright toolkit for local webapp UI and logs","when":"Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/skills/blob/main/skills/webapp-testing/SKILL.md","catch":"Playwright against localhost. Needs a running app; a screenshot is not a test plan.","links":{"self":"/api/skills/webapp-testing","html":"/skills/webapp-testing","markdown":"/skills/webapp-testing.md"}},{"id":"dispatching-parallel-agents","name":"Dispatching Parallel Agents","tagline":"Split independent work across parallel agents","when":"Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/dispatching-parallel-agents/SKILL.md","catch":"Only when 2+ tasks share no state. Sequential work is a false fire.","links":{"self":"/api/skills/dispatching-parallel-agents","html":"/skills/dispatching-parallel-agents","markdown":"/skills/dispatching-parallel-agents.md"}},{"id":"executing-plans","name":"Executing Plans","tagline":"Run a written plan in a separate session with checkpoints","when":"Use when you have a written implementation plan to execute in a separate session with review checkpoints","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/executing-plans/SKILL.md","catch":"Separate session, written plan, checkpoints. Not for writing the plan.","links":{"self":"/api/skills/executing-plans","html":"/skills/executing-plans","markdown":"/skills/executing-plans.md"}},{"id":"finishing-a-development-branch","name":"Finishing a Development Branch","tagline":"Integrate a finished, tested branch","when":"Use when implementation is complete, all tests pass, and you need to decide how to integrate the work","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/finishing-a-development-branch/SKILL.md","catch":"Tests already pass. This decides how to land it — not whether it works.","links":{"self":"/api/skills/finishing-a-development-branch","html":"/skills/finishing-a-development-branch","markdown":"/skills/finishing-a-development-branch.md"}},{"id":"receiving-code-review","name":"Receiving Code Review","tagline":"Verify review feedback before you implement it","when":"Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/receiving-code-review/SKILL.md","catch":"Verify feedback before implementing. Rubber-stamping is the failure mode.","links":{"self":"/api/skills/receiving-code-review","html":"/skills/receiving-code-review","markdown":"/skills/receiving-code-review.md"}},{"id":"requesting-code-review","name":"Requesting Code Review","tagline":"Ask for review after a real feature or before merge","when":"Use when completing tasks, implementing major features, or before merging to verify work meets requirements","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/requesting-code-review/SKILL.md","catch":"After a real feature or before merge. Not a substitute for tests.","links":{"self":"/api/skills/requesting-code-review","html":"/skills/requesting-code-review","markdown":"/skills/requesting-code-review.md"}},{"id":"subagent-driven-development","name":"Subagent-Driven Development","tagline":"Execute a plan with independent subagents in-session","when":"Use when executing implementation plans with independent tasks in the current session","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/subagent-driven-development/SKILL.md","catch":"In-session subagents. Conflicts with executing-plans (which wants a separate session).","links":{"self":"/api/skills/subagent-driven-development","html":"/skills/subagent-driven-development","markdown":"/skills/subagent-driven-development.md"}},{"id":"systematic-debugging","name":"Systematic Debugging","tagline":"Root-cause the bug before proposing a fix","when":"Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/systematic-debugging/SKILL.md","catch":"Evidence lives outside the agent. Reproduce the failure, read the log, then patch. Do not skip verification because the stack trace looked obvious.","links":{"self":"/api/skills/systematic-debugging","html":"/skills/systematic-debugging","markdown":"/skills/systematic-debugging.md"}},{"id":"test-driven-development","name":"Test-Driven Development","tagline":"Write the failing test before implementation","when":"Use when implementing any feature or bugfix, before writing implementation code","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/test-driven-development/SKILL.md","catch":"Red, then green, then code. Agents skip the red step constantly.","links":{"self":"/api/skills/test-driven-development","html":"/skills/test-driven-development","markdown":"/skills/test-driven-development.md"}},{"id":"using-git-worktrees","name":"Using Git Worktrees","tagline":"Isolate feature work in a git worktree","when":"Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/using-git-worktrees/SKILL.md","catch":"Isolate via worktree. No-op if you ignore it and stay on the dirty branch.","links":{"self":"/api/skills/using-git-worktrees","html":"/skills/using-git-worktrees","markdown":"/skills/using-git-worktrees.md"}},{"id":"verification-before-completion","name":"Verification Before Completion","tagline":"Run the proof before claiming done","when":"Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/verification-before-completion/SKILL.md","catch":"Run the proof before claiming done. Agents say “done” without running the command.","links":{"self":"/api/skills/verification-before-completion","html":"/skills/verification-before-completion","markdown":"/skills/verification-before-completion.md"}},{"id":"writing-plans","name":"Writing Plans","tagline":"Bite-sized implementation plan after a spec exists","when":"Use when you already have a spec or requirements for a multi-step task and need a bite-sized implementation plan before touching code — not for writing the spec itself.","license":"MIT","sourceUrl":"https://github.com/obra/superpowers/blob/main/skills/writing-plans/SKILL.md","catch":"Bite-sized steps after a spec exists. Not for writing the spec (that’s spec-driven-development).","links":{"self":"/api/skills/writing-plans","html":"/skills/writing-plans","markdown":"/skills/writing-plans.md"}},{"id":"api-and-interface-design","name":"API and Interface Design","tagline":"Stable APIs, module boundaries, and public contracts","when":"Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/api-and-interface-design/SKILL.md","catch":"Encyclopedia When from addyosmani/agent-skills. Never-fire if the agent does not load it.","links":{"self":"/api/skills/api-and-interface-design","html":"/skills/api-and-interface-design","markdown":"/skills/api-and-interface-design.md"}},{"id":"browser-testing-with-devtools","name":"Browser Testing with DevTools","tagline":"Chrome DevTools MCP for real-browser evidence","when":"Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/browser-testing-with-devtools/SKILL.md","catch":"Requires the chrome-devtools MCP server. Without it, this is a prompt, not a browser.","links":{"self":"/api/skills/browser-testing-with-devtools","html":"/skills/browser-testing-with-devtools","markdown":"/skills/browser-testing-with-devtools.md"}},{"id":"ci-cd-and-automation","name":"CI/CD and Automation","tagline":"Build, test, and deploy pipelines as quality gates","when":"Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/ci-cd-and-automation/SKILL.md","catch":"Encyclopedia When from addyosmani/agent-skills. Not a CI vendor. Never-fire if the agent does not load it.","links":{"self":"/api/skills/ci-cd-and-automation","html":"/skills/ci-cd-and-automation","markdown":"/skills/ci-cd-and-automation.md"}},{"id":"code-review-and-quality","name":"Code Review and Quality","tagline":"Multi-axis review before a change lands","when":"Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/code-review-and-quality/SKILL.md","catch":"This is a review workflow, not AGENTS.md. Do not treat it as project agent instructions.","links":{"self":"/api/skills/code-review-and-quality","html":"/skills/code-review-and-quality","markdown":"/skills/code-review-and-quality.md"}},{"id":"code-simplification","name":"Code Simplification","tagline":"Clarify working code without changing behavior","when":"Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/code-simplification/SKILL.md","catch":"Clarify without changing behavior. Easy to “simplify” into a rewrite.","links":{"self":"/api/skills/code-simplification","html":"/skills/code-simplification","markdown":"/skills/code-simplification.md"}},{"id":"constraint-driven-development","name":"Constraint-Driven Development","tagline":"Write the quality bar so agents cannot quietly lower it","when":"Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says \"set up constraints\" or \"define our standards\", when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/constraint-driven-development/SKILL.md","catch":"Writes CONSTRAINTS.md. Useless if nobody reads it, or if the agent quietly lowers the bar anyway.","links":{"self":"/api/skills/constraint-driven-development","html":"/skills/constraint-driven-development","markdown":"/skills/constraint-driven-development.md"}},{"id":"deprecation-and-migration","name":"Deprecation and Migration","tagline":"Sunset, migrate, and expand/contract without downtime","when":"Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/deprecation-and-migration/SKILL.md","catch":"Expand/contract, then delete. Not a license to drop a column on Friday.","links":{"self":"/api/skills/deprecation-and-migration","html":"/skills/deprecation-and-migration","markdown":"/skills/deprecation-and-migration.md"}},{"id":"documentation-and-adrs","name":"Documentation and ADRs","tagline":"Record decisions so the next engineer and agent can follow","when":"Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/documentation-and-adrs/SKILL.md","catch":"Record the decision. Agents write ADRs nobody asked for.","links":{"self":"/api/skills/documentation-and-adrs","html":"/skills/documentation-and-adrs","markdown":"/skills/documentation-and-adrs.md"}},{"id":"doubt-driven-development","name":"Doubt-Driven Development","tagline":"Adversarial review of high-stakes decisions before they stand","when":"Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/doubt-driven-development/SKILL.md","catch":"Adversarial review before the decision stands. Slow by design; skip it and you get confident wrongness.","links":{"self":"/api/skills/doubt-driven-development","html":"/skills/doubt-driven-development","markdown":"/skills/doubt-driven-development.md"}},{"id":"frontend-ui-engineering","name":"Frontend UI Engineering","tagline":"Production-quality accessible, responsive UI","when":"Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/frontend-ui-engineering/SKILL.md","catch":"Production a11y/responsive UI. Overlaps frontend-design; this one is engineering, not vibe.","links":{"self":"/api/skills/frontend-ui-engineering","html":"/skills/frontend-ui-engineering","markdown":"/skills/frontend-ui-engineering.md"}},{"id":"git-workflow-and-versioning","name":"Git Workflow and Versioning","tagline":"Commits, branches, PRs, tags, and version bumps","when":"Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/git-workflow-and-versioning/SKILL.md","catch":"Commits, PRs, tags. Not using-git-worktrees. Never-fire if the agent does not load it.","links":{"self":"/api/skills/git-workflow-and-versioning","html":"/skills/git-workflow-and-versioning","markdown":"/skills/git-workflow-and-versioning.md"}},{"id":"idea-refine","name":"Idea Refine","tagline":"Diverge, then converge a vague idea into a sharp concept","when":"Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on \"ideate\", \"refine this idea\", or \"stress-test my plan\".","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/idea-refine/SKILL.md","catch":"Diverge, then converge. Idle unless the idea is still vague.","links":{"self":"/api/skills/idea-refine","html":"/skills/idea-refine","markdown":"/skills/idea-refine.md"}},{"id":"interview-me","name":"Interview Me","tagline":"One-question interviews until the real intent is clear","when":"Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified (\"build me X\" without \"for whom\" or \"why now\"), when the user explicitly invokes (\"interview me\", \"grill me\", \"are we sure?\", \"stress-test my thinking\"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/interview-me/SKILL.md","catch":"One question at a time until intent is clear. Annoying if you already know what you want.","links":{"self":"/api/skills/interview-me","html":"/skills/interview-me","markdown":"/skills/interview-me.md"}},{"id":"observability-and-instrumentation","name":"Observability and Instrumentation","tagline":"Logs, metrics, traces so production is diagnosable","when":"Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/observability-and-instrumentation/SKILL.md","catch":"Logs, metrics, traces. Not Sentry-the-product. Never-fire if the agent does not load it.","links":{"self":"/api/skills/observability-and-instrumentation","html":"/skills/observability-and-instrumentation","markdown":"/skills/observability-and-instrumentation.md"}},{"id":"performance-optimization","name":"Performance Optimization","tagline":"Frontend, backend, and query performance with evidence","when":"Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/performance-optimization/SKILL.md","catch":"Needs a metric. Profiling theater without a number is not this skill.","links":{"self":"/api/skills/performance-optimization","html":"/skills/performance-optimization","markdown":"/skills/performance-optimization.md"}},{"id":"planning-and-task-breakdown","name":"Planning and Task Breakdown","tagline":"Turn a spec into ordered, estimable tasks","when":"Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/planning-and-task-breakdown/SKILL.md","catch":"After a spec. Overlaps writing-plans. Never-fire if the agent does not load it.","links":{"self":"/api/skills/planning-and-task-breakdown","html":"/skills/planning-and-task-breakdown","markdown":"/skills/planning-and-task-breakdown.md"}},{"id":"security-and-hardening","name":"Security and Hardening","tagline":"Input, auth, data, and supply-chain hardening","when":"Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/security-and-hardening/SKILL.md","catch":"Input, auth, data, supply-chain. Not a pentest and not Sentry security-review.","links":{"self":"/api/skills/security-and-hardening","html":"/skills/security-and-hardening","markdown":"/skills/security-and-hardening.md"}},{"id":"shipping-and-launch","name":"Shipping and Launch","tagline":"Pre-launch checklist, rollout, and rollback","when":"Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/shipping-and-launch/SKILL.md","catch":"Checklist, rollout, rollback. Not a deploy button.","links":{"self":"/api/skills/shipping-and-launch","html":"/skills/shipping-and-launch","markdown":"/skills/shipping-and-launch.md"}},{"id":"source-driven-development","name":"Source-Driven Development","tagline":"Cite official docs instead of remembered APIs","when":"Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/source-driven-development/SKILL.md","catch":"Cite official docs. Agents still answer from memory.","links":{"self":"/api/skills/source-driven-development","html":"/skills/source-driven-development","markdown":"/skills/source-driven-development.md"}},{"id":"spec-driven-development","name":"Spec-Driven Development","tagline":"Write the spec first when none exists yet","when":"Use when starting a new project, feature, or significant change and no specification exists yet. Write the spec first. Distinct from Writing Plans, which assumes a spec already exists.","license":"MIT","sourceUrl":"https://github.com/addyosmani/agent-skills/blob/main/skills/spec-driven-development/SKILL.md","catch":"Write the spec first when none exists. Distinct from writing-plans, which assumes a spec already exists.","links":{"self":"/api/skills/spec-driven-development","html":"/skills/spec-driven-development","markdown":"/skills/spec-driven-development.md"}},{"id":"vercel-react-best-practices","name":"Vercel React Best Practices","tagline":"Vercel Engineering React and Next.js performance patterns","when":"React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","license":"MIT","sourceUrl":"https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md","catch":"Vercel Engineering React/Next performance patterns. MIT in SKILL.md frontmatter; vercel-labs/agent-skills has no LICENSE file. Broad React triggers.","links":{"self":"/api/skills/vercel-react-best-practices","html":"/skills/vercel-react-best-practices","markdown":"/skills/vercel-react-best-practices.md"}},{"id":"vercel-composition-patterns","name":"Vercel Composition Patterns","tagline":"React composition that scales past boolean props","when":"React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.","license":"MIT","sourceUrl":"https://github.com/vercel-labs/agent-skills/blob/main/skills/composition-patterns/SKILL.md","catch":"Compound components and boolean-prop cleanup, including React 19. Same undeclared-repo LICENSE. Not a performance skill.","links":{"self":"/api/skills/vercel-composition-patterns","html":"/skills/vercel-composition-patterns","markdown":"/skills/vercel-composition-patterns.md"}},{"id":"vercel-react-native-skills","name":"Vercel React Native Skills","tagline":"React Native and Expo performance and native-module patterns","when":"React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.","license":"MIT","sourceUrl":"https://github.com/vercel-labs/agent-skills/blob/main/skills/react-native-skills/SKILL.md","catch":"React Native/Expo lists, animations, native modules. Same undeclared-repo LICENSE. Idle on web React.","links":{"self":"/api/skills/vercel-react-native-skills","html":"/skills/vercel-react-native-skills","markdown":"/skills/vercel-react-native-skills.md"}},{"id":"use-railway","name":"Use Railway","tagline":"Railway signup, deploy, services, and infrastructure ops","when":"Operate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services and databases, manage object storage buckets, deploy code, configure infrastructure as code, environments and variables, manage domains, troubleshoot failures, check status and metrics, manage feature flags, set up Railway agent tooling, and query Railway docs. Use this skill whenever the user mentions Railway, feature flags, flag rollout, targeting rules, signing up, creating an account, registering, logging in, deployments, services, environments, buckets, object storage, build failures, agent setup, MCP, or infrastructure operations, even if they don't say \"Railway\" explicitly. Also invoke this skill when the user asks to be signed up, registered, or onboarded to Railway: do not refuse — drive them through the unauthed `railway up` flow (deploys + signs up on the fly) or `railway login` (which creates new accounts on the fly).","license":"MIT","sourceUrl":"https://github.com/railwayapp/railway-skills/blob/main/plugins/railway/skills/use-railway/SKILL.md","catch":"False-fires on feature flags, MCP, and signup. Drives `railway up` for signup. A free tier exists.","links":{"self":"/api/skills/use-railway","html":"/skills/use-railway","markdown":"/skills/use-railway.md"}},{"id":"wrangler","name":"Wrangler","tagline":"Cloudflare Workers CLI, before you type it","when":"Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/wrangler/SKILL.md","catch":"Workers CLI for KV/R2/D1/Queues before you type it. Pulls a non-Cloudflare deploy toward wrangler.","links":{"self":"/api/skills/wrangler","html":"/skills/wrangler","markdown":"/skills/wrangler.md"}},{"id":"workers-best-practices","name":"Workers Best Practices","tagline":"Production Workers anti-patterns","when":"Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/workers-best-practices/SKILL.md","catch":"Production Workers anti-patterns (streaming, globals, bindings). Not a generic JavaScript review.","links":{"self":"/api/skills/workers-best-practices","html":"/skills/workers-best-practices","markdown":"/skills/workers-best-practices.md"}},{"id":"durable-objects","name":"Durable Objects","tagline":"Stateful coordination on Workers","when":"Create and review Cloudflare Durable Objects. Use when building stateful coordination (chat rooms, multiplayer games, booking systems), implementing RPC methods, SQLite storage, alarms, WebSockets, or reviewing DO code for best practices. Covers Workers integration, wrangler config, and testing with Vitest. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/durable-objects/SKILL.md","catch":"Stateful Durable Objects (SQLite, alarms, WebSockets). False-fires on any “stateful agent” that isn’t a DO.","links":{"self":"/api/skills/durable-objects","html":"/skills/durable-objects","markdown":"/skills/durable-objects.md"}},{"id":"turnstile-spin","name":"Turnstile Spin","tagline":"Bot check via Cloudflare Turnstile","when":"Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it where user requests need bot verification (form submissions, SPA actions, API endpoints, download links, comment or vote submissions, etc.), wire canonical server-side siteverify in the customer's existing backend, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form or endpoint from bots, or fix a Turnstile integration. Mirrors developers.cloudflare.com/turnstile/spin.","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/turnstile-spin/SKILL.md","catch":"End-to-end Turnstile widget plus siteverify. A generic captcha/bot-check still gets Turnstile.","links":{"self":"/api/skills/turnstile-spin","html":"/skills/turnstile-spin","markdown":"/skills/turnstile-spin.md"}},{"id":"sandbox-stable","name":"Sandbox Stable","tagline":"@cloudflare/sandbox on the default tag","when":"Use when building or changing Cloudflare Sandbox apps on the current stable @cloudflare/sandbox package (default npm tag)—commands, sessions, files, ports, tunnels, terminals, bridge, production, or deprecated-API cleanup while staying on stable. Not for @cloudflare/sandbox@next (use sandbox-next) or for porting to 1.0 (use sandbox-migrate-to-next).","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/sandbox-stable/SKILL.md","catch":"@cloudflare/sandbox on the default tag. Wrong sibling if the app is on @next.","links":{"self":"/api/skills/sandbox-stable","html":"/skills/sandbox-stable","markdown":"/skills/sandbox-stable.md"}},{"id":"sandbox-next","name":"Sandbox Next","tagline":"Sandbox SDK 1.0 preview tag","when":"Use when building or changing Cloudflare Sandbox apps on @cloudflare/sandbox@next (Sandbox SDK 1.0 preview)—code execution, AI runners, interpreters, CI-like jobs, terminals, files, mounts, tunnels, preview URLs, lifecycle, or errors. Not for the default stable package (use sandbox-stable) or for porting stable to @next (use sandbox-migrate-to-next).","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/sandbox-next/SKILL.md","catch":"Preview Catch: this is @cloudflare/sandbox@next, not the stable default. Vendor skill for Cloudflare.","links":{"self":"/api/skills/sandbox-next","html":"/skills/sandbox-next","markdown":"/skills/sandbox-next.md"}},{"id":"cloudflare-email-service","name":"Cloudflare Email Service","tagline":"Send and route mail from Workers","when":"Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like \"add email to my Worker\" — this skill has critical config details.","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/cloudflare-email-service/SKILL.md","catch":"Workers email send/route and SPF/DKIM. “Add email” on a non-Workers app still steers here.","links":{"self":"/api/skills/cloudflare-email-service","html":"/skills/cloudflare-email-service","markdown":"/skills/cloudflare-email-service.md"}},{"id":"agents-sdk","name":"Agents SDK","tagline":"Stateful agents on Cloudflare Workers","when":"Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","license":"Apache-2.0","sourceUrl":"https://github.com/cloudflare/skills/blob/main/skills/agents-sdk/SKILL.md","catch":"Cloudflare Agents SDK on Workers (state, RPC, Workflows). “MCP/chat agent” triggers steal from the MCP cluster.","links":{"self":"/api/skills/agents-sdk","html":"/skills/agents-sdk","markdown":"/skills/agents-sdk.md"}},{"id":"agents-md","name":"Agents.md","tagline":"This writes AGENTS.md, not a skill","when":"Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/agents-md/SKILL.md","catch":"Loud Catch: this IS AGENTS.md / CLAUDE.md, not an agent skill. Do not confuse it with SKILL.md. Vendor skill from Sentry.","links":{"self":"/api/skills/agents-md","html":"/skills/agents-md","markdown":"/skills/agents-md.md"}},{"id":"claude-settings-audit","name":"Claude Settings Audit","tagline":"permissions.json from the repo shape","when":"Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/claude-settings-audit/SKILL.md","catch":"Writes Claude Code settings.json allowlists from repo shape. Sentry conventions leak; a generic repo still gets Sentry-shaped permissions.","links":{"self":"/api/skills/claude-settings-audit","html":"/skills/claude-settings-audit","markdown":"/skills/claude-settings-audit.md"}},{"id":"django-access-review","name":"Django Access Review","tagline":"IDOR and tenant isolation in Django","when":"Django access control and IDOR security review. Use when reviewing Django views, DRF viewsets, ORM queries, or any Python/Django code handling user authorization. Trigger keywords: \"IDOR\", \"access control\", \"authorization\", \"Django permissions\", \"object permissions\", \"tenant isolation\", \"broken access\".","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/django-access-review/SKILL.md","catch":"IDOR and tenant isolation in Django views/ORM. Idle off Django; not a generic auth review.","links":{"self":"/api/skills/django-access-review","html":"/skills/django-access-review","markdown":"/skills/django-access-review.md"}},{"id":"django-perf-review","name":"Django Perf Review","tagline":"N+1 and queryset audits","when":"Django performance code review. Use when asked to \"review Django performance\", \"find N+1 queries\", \"optimize Django\", \"check queryset performance\", \"database performance\", \"Django ORM issues\", or audit Django code for performance problems.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/django-perf-review/SKILL.md","catch":"N+1 and queryset audit, not a general perf skill. “Optimize Django” false-fires when the bottleneck isn’t the ORM.","links":{"self":"/api/skills/django-perf-review","html":"/skills/django-perf-review","markdown":"/skills/django-perf-review.md"}},{"id":"sentry-doc-coauthoring","name":"Sentry Doc Coauthoring","tagline":"Structured pass with the human still in it","when":"Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/doc-coauthoring/SKILL.md","catch":"Human-in-the-loop doc loop from getsentry/skills. Twin of Anthropic doc-coauthoring; never-fires if the agent just writes the doc.","links":{"self":"/api/skills/sentry-doc-coauthoring","html":"/skills/sentry-doc-coauthoring","markdown":"/skills/sentry-doc-coauthoring.md"}},{"id":"gh-review-requests","name":"GH Review Requests","tagline":"Unread review-request notifications","when":"Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to \"find PRs I need to review\", \"show my review requests\", \"what needs my review\", \"fetch GitHub review requests\", or \"check team review queue\".","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/gh-review-requests/SKILL.md","catch":"Fetches unread GitHub review-request notifications. Needs gh + a team; an empty inbox looks like “no reviews.”","links":{"self":"/api/skills/gh-review-requests","html":"/skills/gh-review-requests","markdown":"/skills/gh-review-requests.md"}},{"id":"gha-security-review","name":"GHA Security Review","tagline":"Pwn-request and workflow injection","when":"GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to \"review GitHub Actions\", \"audit workflows\", \"check CI security\", \"GHA security\", \"workflow security review\", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks. Exploitation-focused with concrete PoC scenarios.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/gha-security-review/SKILL.md","catch":"Pwn-request and expression-injection in .github/workflows. Exploitation-shaped; not a green-CI checklist.","links":{"self":"/api/skills/gha-security-review","html":"/skills/gha-security-review","markdown":"/skills/gha-security-review.md"}},{"id":"iterate-pr","name":"Iterate PR","tagline":"CI + review loop until the PR is green","when":"Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or merge gates.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/iterate-pr/SKILL.md","catch":"Loops CI and review until green, and will not wait for human approval or merge gates. Keeps pushing a draft you wanted parked.","links":{"self":"/api/skills/iterate-pr","html":"/skills/iterate-pr","markdown":"/skills/iterate-pr.md"}},{"id":"pr-writer","name":"PR Writer","tagline":"Reviewer-facing title and body","when":"Create or refresh reviewer-facing PR titles and descriptions. Use when opening a PR, updating its title or body, or preparing branch changes for review.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/pr-writer/SKILL.md","catch":"Reviewer-facing title and body only. Will rewrite a PR description you already wrote.","links":{"self":"/api/skills/pr-writer","html":"/skills/pr-writer","markdown":"/skills/pr-writer.md"}},{"id":"prompt-optimizer","name":"Prompt Optimizer","tagline":"Evals and model-family adapters","when":"Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/prompt-optimizer/SKILL.md","catch":"Prompt evals and OpenAI/Claude/Gemini adapters. Not product copy; will “optimize” a prompt that wasn’t the job.","links":{"self":"/api/skills/prompt-optimizer","html":"/skills/prompt-optimizer","markdown":"/skills/prompt-optimizer.md"}},{"id":"skill-scanner","name":"Skill Scanner","tagline":"Audit a SKILL.md before you install it","when":"Scan agent skills for security issues. Use when asked to \"scan a skill\", \"audit a skill\", \"review skill security\", \"check skill for injection\", \"validate SKILL.md\", or assess whether an agent skill is safe to install. Checks for prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/skill-scanner/SKILL.md","catch":"Audits a SKILL.md for injection and secrets before install. Scanning is not the same as running the skill.","links":{"self":"/api/skills/skill-scanner","html":"/skills/skill-scanner","markdown":"/skills/skill-scanner.md"}},{"id":"find-bugs","name":"Find Bugs","tagline":"Bugs on this branch, not the whole repo","when":"Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/find-bugs/SKILL.md","catch":"Bugs on this branch, not the whole repo. A repo-wide “find bugs” is a false fire.","links":{"self":"/api/skills/find-bugs","html":"/skills/find-bugs","markdown":"/skills/find-bugs.md"}},{"id":"security-review","name":"Security Review","tagline":"OWASP-style pass with confidence scores","when":"Security code review for vulnerabilities. Use when asked to \"security review\", \"find vulnerabilities\", \"check for security issues\", \"audit security\", \"OWASP review\", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/security-review/SKILL.md","catch":"OWASP-style pass with confidence scores. Overlaps find-bugs and gha-security-review; not Sentry-product config.","links":{"self":"/api/skills/security-review","html":"/skills/security-review","markdown":"/skills/security-review.md"}},{"id":"document-api-endpoint","name":"Document API Endpoint","tagline":"Sentry @extend_schema and TypedDicts","when":"Document and type a Sentry API endpoint. Write or fix @extend_schema decorators, specify response TypedDicts, type request parameters, correct type drift between the declared schema and the runtime response, and validate the generated spec. Use when asked to \"document an endpoint\", \"add OpenAPI docs\", \"add/fix @extend_schema\", \"type an endpoint response\", \"fix the response type\", \"fix type drift\", \"reuse a response type\", \"split an overloaded endpoint\", \"specify the response schema\", \"add a TypedDict response\", \"migrate a legacy api-docs path\", \"fix a parameter type\", or \"make an endpoint public\" / \"promote an endpoint\" (promotion is one section here).","license":"Apache-2.0","sourceUrl":"https://github.com/getsentry/skills/blob/main/skills/document-api-endpoint/SKILL.md","catch":"Sentry @extend_schema and response TypedDicts. Dead outside getsentry API views.","links":{"self":"/api/skills/document-api-endpoint","html":"/skills/document-api-endpoint","markdown":"/skills/document-api-endpoint.md"}},{"id":"claude-security","name":"Claude Security","tagline":"In-session scan, then patches you apply","when":"The Claude Security menu — pick a job: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose).","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/claude-security/skills/claude-security/SKILL.md","catch":"In-session scan, then patch files you apply. Claude Code plugin layout; not Sentry security-review.","links":{"self":"/api/skills/claude-security","html":"/skills/claude-security","markdown":"/skills/claude-security.md"}},{"id":"claude-automation-recommender","name":"Claude Automation Recommender","tagline":"Hooks, skills, MCP — recommendations only","when":"Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/claude-code-setup/skills/claude-automation-recommender/SKILL.md","catch":"Recommends hooks, skills, and MCP for Claude Code — it does not install them. Vendor lock.","links":{"self":"/api/skills/claude-automation-recommender","html":"/skills/claude-automation-recommender","markdown":"/skills/claude-automation-recommender.md"}},{"id":"agent-development","name":"Agent Development","tagline":"Claude Code subagent frontmatter","when":"This skill should be used when the user asks to \"create an agent\", \"add an agent\", \"write a subagent\", \"agent frontmatter\", \"when to use description\", \"agent examples\", \"agent tools\", \"agent colors\", \"autonomous agent\", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/plugin-dev/skills/agent-development/SKILL.md","catch":"Claude Code subagent frontmatter (when-to-use, tools, colors). “Create an agent” outside plugins is a false fire.","links":{"self":"/api/skills/agent-development","html":"/skills/agent-development","markdown":"/skills/agent-development.md"}},{"id":"command-development","name":"Command Development","tagline":"Slash commands for Claude Code plugins","when":"This skill should be used when the user asks to \"create a slash command\", \"add a command\", \"write a custom command\", \"define command arguments\", \"use command frontmatter\", \"organize commands\", \"create command with file references\", \"interactive command\", \"use AskUserQuestion in command\", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/plugin-dev/skills/command-development/SKILL.md","catch":"Slash commands and AskUserQuestion inside Claude Code plugins. Not a Unix CLI skill.","links":{"self":"/api/skills/command-development","html":"/skills/command-development","markdown":"/skills/command-development.md"}},{"id":"hook-development","name":"Hook Development","tagline":"PreToolUse and friends, in plugins","when":"This skill should be used when the user asks to \"create a hook\", \"add a PreToolUse/PostToolUse/Stop hook\", \"validate tool use\", \"implement prompt-based hooks\", \"use ${CLAUDE_PLUGIN_ROOT}\", \"set up event-driven automation\", \"block dangerous commands\", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/plugin-dev/skills/hook-development/SKILL.md","catch":"PreToolUse/PostToolUse/Stop hooks with ${CLAUDE_PLUGIN_ROOT}. Never-fires without that plugin layout.","links":{"self":"/api/skills/hook-development","html":"/skills/hook-development","markdown":"/skills/hook-development.md"}},{"id":"plugin-structure","name":"Plugin Structure","tagline":"plugin.json at the root, components beside it","when":"This skill should be used when the user asks to \"create a plugin\", \"scaffold a plugin\", \"understand plugin structure\", \"organize plugin components\", \"set up plugin.json\", \"use ${CLAUDE_PLUGIN_ROOT}\", \"add commands/agents/skills/hooks\", \"configure auto-discovery\", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/plugin-dev/skills/plugin-structure/SKILL.md","catch":"plugin.json scaffold and auto-discovery. First-step only; overlaps the other plugin-dev siblings.","links":{"self":"/api/skills/plugin-structure","html":"/skills/plugin-structure","markdown":"/skills/plugin-structure.md"}},{"id":"plugin-settings","name":"Plugin Settings","tagline":".local.md config for a plugin","when":"This skill should be used when the user asks about \"plugin settings\", \"store plugin configuration\", \"user-configurable plugin\", \".local.md files\", \"plugin state files\", \"read YAML frontmatter\", \"per-project plugin settings\", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/plugin-dev/skills/plugin-settings/SKILL.md","catch":"Per-project .claude/<plugin>.local.md YAML. “Plugin settings” in an editor is a false fire.","links":{"self":"/api/skills/plugin-settings","html":"/skills/plugin-settings","markdown":"/skills/plugin-settings.md"}},{"id":"build-mcp-app","name":"Build MCP App","tagline":"In-chat widgets on an MCP server","when":"This skill should be used when the user wants to build an \"MCP app\", add \"interactive UI\" or \"widgets\" to an MCP server, \"render components in chat\", build \"MCP UI resources\", make a tool that shows a \"form\", \"picker\", \"dashboard\" or \"confirmation dialog\" inline in the conversation, or mentions \"apps SDK\" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/mcp-server-dev/skills/build-mcp-app/SKILL.md","catch":"In-chat MCP App widgets after the server exists. Not how to build the server (that’s HOLD build-mcp-server).","links":{"self":"/api/skills/build-mcp-app","html":"/skills/build-mcp-app","markdown":"/skills/build-mcp-app.md"}},{"id":"build-mcpb","name":"Build MCPB","tagline":"Bundle a local MCP with its runtime","when":"This skill should be used when the user wants to \"package an MCP server\", \"bundle an MCP\", \"make an MCPB\", \"ship a local MCP server\", \"distribute a local MCP\", discusses \".mcpb files\", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.","license":"Apache-2.0","sourceUrl":"https://github.com/anthropics/claude-plugins-official/blob/main/plugins/mcp-server-dev/skills/build-mcpb/SKILL.md","catch":"Bundles a local MCP plus runtime as .mcpb. Desktop/filesystem MCP; not a hosted-server tutorial.","links":{"self":"/api/skills/build-mcpb","html":"/skills/build-mcpb","markdown":"/skills/build-mcpb.md"}},{"id":"expo-animation","name":"Expo Animation","tagline":"Reanimated, Gesture Handler, and haptics on device","when":"Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and expo-haptics. Use when animating anything in an Expo app, adding gestures, sheets, screen transitions, press feedback or haptics, or fixing motion that stutters on device. For web animation use `animate`.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-animation/SKILL.md","catch":"Reanimated/GH/haptics; wrong for web CSS motion; fights expo-ui (don’t use Reanimated for sheets).","links":{"self":"/api/skills/expo-animation","html":"/skills/expo-animation","markdown":"/skills/expo-animation.md"}},{"id":"expo-app-clip","name":"Expo App Clip","tagline":"iOS App Clip target beside the parent Expo app","when":"Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-app-clip/SKILL.md","catch":"iOS Clip/AASA only; dead on Android/web.","links":{"self":"/api/skills/expo-app-clip","html":"/skills/expo-app-clip","markdown":"/skills/expo-app-clip.md"}},{"id":"expo-brownfield","name":"Expo Brownfield","tagline":"Embed Expo in an existing Swift or Kotlin app","when":"Integrate Expo and React Native into an existing native iOS or Android app. Use when the user mentions brownfield, embedding React Native in a native app, AAR/XCFramework, or adding Expo to an existing Kotlin/Swift project. Covers both the isolated approach and the integrated approach.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-brownfield/SKILL.md","catch":"embed-in-existing-native only; dead on greenfield Expo.","links":{"self":"/api/skills/expo-brownfield","html":"/skills/expo-brownfield","markdown":"/skills/expo-brownfield.md"}},{"id":"expo-data-fetching","name":"Expo Data Fetching","tagline":"Fetch, React Query, SWR, and Expo Router loaders","when":"Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (`useLoaderData`).","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-data-fetching/SKILL.md","catch":"“ANY network request” steals generic fetch/SWR outside Expo.","links":{"self":"/api/skills/expo-data-fetching","html":"/skills/expo-data-fetching","markdown":"/skills/expo-data-fetching.md"}},{"id":"expo-design-system","name":"Expo Design System","tagline":"Tokens, variants, and an in-app component library for Expo","when":"Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when creating or organizing theme files and design tokens (theme.ts / theme/), extending an existing theme or styling library (NativeWind, Tamagui, Restyle, Unistyles) in its own idiom, standardizing styles so screens (including AI-generated ones) look consistent and polished, building an in-app component library, or auditing an app for design-system drift (hardcoded colors, spacing, fonts). For platform styling specifics (semantic colors, HIG rules, native controls) use expo-native-ui; for folder layout of a new app use expo-project-structure.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-design-system/SKILL.md","catch":"Expo token/theme kit; twin of frontend-design if you drop the Expo scope.","links":{"self":"/api/skills/expo-design-system","html":"/skills/expo-design-system","markdown":"/skills/expo-design-system.md"}},{"id":"expo-dev-client","name":"Expo Dev Client","tagline":"Local and TestFlight Expo development clients","when":"Build and distribute Expo development clients locally or via TestFlight for internal testing. For production TestFlight releases and store submission, use the eas-app-stores skill.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-dev-client/SKILL.md","catch":"internal dev-client builds; agents mix it with paid eas-app-stores TestFlight.","links":{"self":"/api/skills/expo-dev-client","html":"/skills/expo-dev-client","markdown":"/skills/expo-dev-client.md"}},{"id":"expo-dom","name":"Expo DOM","tagline":"Web code in a native webview, incrementally","when":"Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally. For the end-to-end migration of a whole web app, use the expo-web-to-native skill.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-dom/SKILL.md","catch":"webview DOM components only; not a full web→native port.","links":{"self":"/api/skills/expo-dom","html":"/skills/expo-dom","markdown":"/skills/expo-dom.md"}},{"id":"expo-examples","name":"Expo Examples","tagline":"Adapt with-* starters from expo/examples","when":"Adapt a canonical `with-*` from expo/examples (~70 integrations) or `npx create-expo --example`. Use when starting from an official Expo example rather than a blank app. Never scaffold on top of an existing app. Distinct from expo-project-structure (new-app folder layout, not example starters).","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-examples/SKILL.md","catch":"Not full apps — managed single-screen patterns. catalog.md drifts; confirm live list. Never scaffold on top of an existing app. Distinct from expo-project-structure.","links":{"self":"/api/skills/expo-examples","html":"/skills/expo-examples","markdown":"/skills/expo-examples.md"}},{"id":"expo-migrate-module","name":"Expo Migrate Module","tagline":"Swift Expo module 1.0 DSL → 2.0 macros","when":"Swift Expo module 1.0 DSL → 2.0 macros (`@ExpoModule`, `@JS`, …). Preserve the JS contract. Use when migrating an existing Swift module off the definition DSL onto Expo Modules API 2.0 macros. Requires expo ≥ 57.0.7. Not for new modules (expo-module), not SDK upgrades (expo-upgrade), not Android/Kotlin.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo-experiments/skills/expo-migrate-module/SKILL.md","catch":"Experiments path, not the main expo plugin. Requires expo ≥ 57.0.7. Not for new modules (expo-module), not SDK upgrades (expo-upgrade), not Android/Kotlin.","links":{"self":"/api/skills/expo-migrate-module","html":"/skills/expo-migrate-module","markdown":"/skills/expo-migrate-module.md"}},{"id":"expo-module","name":"Expo Module","tagline":"New Expo Modules API in Swift, Kotlin, and TypeScript","when":"Guide for creating and writing Expo native modules and views using the Expo Modules API (Swift, Kotlin, TypeScript). Covers module definition DSL, native views, shared objects, config plugins, lifecycle hooks, autolinking, and type system. Use when building or modifying native modules for Expo. Not for migrating an existing Swift module from the definition DSL to the Expo Modules API 2.0 macros; use expo-migrate-module (from the expo-experiments plugin) for that.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-module/SKILL.md","catch":"native module authors (Swift/Kotlin); never-fires on JS-only Expo apps.","links":{"self":"/api/skills/expo-module","html":"/skills/expo-module","markdown":"/skills/expo-module.md"}},{"id":"expo-native-ui","name":"Expo Native UI","tagline":"HIG, semantic color, and SF Symbols on Expo screens","when":"Build beautiful, native-feeling Expo screens. Covers Apple HIG styling, semantic colors, native controls, SF Symbols, media, animations, visual effects, gradients, storage, and responsive layout. For routing and navigation, use the expo-router skill.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-native-ui/SKILL.md","catch":"HIG/SF Symbols screens; look vs @expo/ui primitives (expo-ui).","links":{"self":"/api/skills/expo-native-ui","html":"/skills/expo-native-ui","markdown":"/skills/expo-native-ui.md"}},{"id":"expo-project-structure","name":"Expo Project Structure","tagline":"Folder layout for a new Expo Router app","when":"Folder structure for a new Expo app. Use when scaffolding or laying out a new Expo project with Expo Router, or deciding where a file should live in one. For new projects only — never restructure an existing app to match.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-project-structure/SKILL.md","catch":"new-app folders only; forbids restructuring existing apps.","links":{"self":"/api/skills/expo-project-structure","html":"/skills/expo-project-structure","markdown":"/skills/expo-project-structure.md"}},{"id":"expo-router","name":"Expo Router","tagline":"File-based routes, Stack, NativeTabs, and modals","when":"Navigation and routing for Expo Router. Covers file-based routes, groups and dynamic routes, folder organization, Link with previews and context menus, native Stack, page titles, modals and form sheets, NativeTabs, headers and toolbars, and header search bars.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-router/SKILL.md","catch":"Expo Router file routes only; steals Next.js App Router and React Navigation.","links":{"self":"/api/skills/expo-router","html":"/skills/expo-router","markdown":"/skills/expo-router.md"}},{"id":"expo-ui","name":"Expo UI","tagline":"@expo/ui SwiftUI and Compose primitives","when":"Build native UI with the @expo/ui package: real SwiftUI on iOS and Jetpack Compose on Android. Default to @expo/ui for sheets (BottomSheet), pickers, sliders, toggles, menus, and grouped-form sections — do NOT reach for Reanimated, @gorhom/bottom-sheet, or RN built-in Picker/Switch; use @expo/ui instead. Fall back to RN built-ins only when @expo/ui is missing the component. NOTE: @expo/ui List renders native grouped rows like an iOS Settings screen — it is NOT a virtualized list; use FlatList/FlashList for large datasets. Covers universal components (Host, Column, Row, Button, Text, List, BottomSheet, FieldGroup, Switch, Slider, Picker, Menu), drop-in replacements for RN community libraries, and platform-specific SwiftUI/Jetpack Compose trees. Not for Expo Router navigation, Reanimated, or data fetching.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-ui/SKILL.md","catch":"@expo/ui SwiftUI/Compose controls; not FlashList; not expo-native-ui styling.","links":{"self":"/api/skills/expo-ui","html":"/skills/expo-ui","markdown":"/skills/expo-ui.md"}},{"id":"expo-upgrade","name":"Expo Upgrade","tagline":"Expo SDK upgrades and dependency fixes","when":"Guidelines for upgrading Expo SDK versions and fixing dependency issues.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-upgrade/SKILL.md","catch":"Expo SDK bump cookbook; stale after the next SDK; not a generic RN upgrade.","links":{"self":"/api/skills/expo-upgrade","html":"/skills/expo-upgrade","markdown":"/skills/expo-upgrade.md"}},{"id":"expo-web-to-native","name":"Expo Web to Native","tagline":"Port Next/Vite/CRA to Expo native, screen by screen","when":"Migrate an existing web React app to a native iOS/Android app with Expo. Use when the user wants to turn a website into a mobile app, port a Next.js/Vite/CRA React codebase to React Native, reuse web code on native incrementally, or asks how web idioms (the DOM, CSS, React Router, localStorage, window) map to native. This is the end-to-end migration guide; use the `expo-dom` skill for the DOM-component mechanism itself.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/expo-web-to-native/SKILL.md","catch":"whole-app Next/Vite/CRA → Expo; not expo-dom.","links":{"self":"/api/skills/expo-web-to-native","html":"/skills/expo-web-to-native","markdown":"/skills/expo-web-to-native.md"}},{"id":"eas-app-stores","name":"EAS App Stores","tagline":"EAS build and submit to App Store and Play","when":"EAS service (paid). Deploy Expo apps to the app stores with EAS - build and submit to the iOS App Store, Google Play Store, and TestFlight, configure eas.json build and submit profiles, manage app versions and build numbers, and publish App Store metadata and ASO. Use whenever the user wants to deploy, release, or ship an app to production or the app stores, is preparing a production build, running eas build or eas submit, shipping to TestFlight, bumping version or build numbers, or setting up store listing metadata. For deploying an Expo website or API routes, use the eas-hosting skill.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-app-stores/SKILL.md","catch":"eas build/submit to stores. Free-tier build minutes; Apple/Google developer accounts still cost. Not local expo-dev-client.","links":{"self":"/api/skills/eas-app-stores","html":"/skills/eas-app-stores","markdown":"/skills/eas-app-stores.md"}},{"id":"eas-hosting","name":"EAS Hosting","tagline":"Expo web and API routes via eas deploy","when":"EAS service (paid). Deploy Expo websites and Expo Router API routes to EAS Hosting - export the web bundle, run eas deploy for production and PR preview URLs, manage environment secrets and custom domains, and work within the Cloudflare Workers runtime. Also covers authoring API routes (+api.ts handlers, HTTP methods, request handling, CORS). Use when deploying an Expo web app or API routes, setting up EAS Hosting, or configuring hosting environments and domains. Not for native builds or store releases - use the eas-app-stores skill for those.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-hosting/SKILL.md","catch":"Expo web/API routes via eas deploy (CF Workers). Authoring routes is free; production deploys use plan allowance.","links":{"self":"/api/skills/eas-hosting","html":"/skills/eas-hosting","markdown":"/skills/eas-hosting.md"}},{"id":"eas-observe","name":"EAS Observe","tagline":"expo-observe metrics, 10k MAU free cap","when":"EAS service (paid). Use for anything related to EAS Observe - adding `expo-observe` to an Expo project (AppMetricsRoot/ObserveRoot HOC, markInteractive and ObserveInteractiveMarker, the useObserve hook, the Expo Router / React Navigation integrations for per-route metrics, user-defined events via `Observe.logEvent`, error reporting via ObserveErrorBoundary and `Observe.reportError`, and runtime config such as sampleRate and dispatchInDebug), querying via the EAS CLI (`eas observe:metrics-summary`, `observe:metrics`, `observe:routes`, `observe:events`, `observe:session`, `observe:versions`), interpreting the resulting metrics (cold/warm launch, TTR, TTI, navigation cold/warm TTR, update download, and the TTI frameRate/device/network params for triaging slow startups), or shipping an Observe integration inside a third-party package.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-observe/SKILL.md","catch":"expo-observe metrics. Free plan up to 10k MAU, then paid. Not generic analytics.","links":{"self":"/api/skills/eas-observe","html":"/skills/eas-observe","markdown":"/skills/eas-observe.md"}},{"id":"eas-simulator","name":"EAS Simulator","tagline":"Remote iOS/Android sim on EAS cloud","when":"EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any `eas simulator:*` commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to run/install/screenshot my app', 'I'm on Linux/Cursor and need an iOS device', 'no sim on this box / headless CI', 'let an agent click through my app and screenshot it', 'test my dev build on a remote sim with live reload', 'stream a sim to my browser' - even when they don't say 'EAS Simulator' or 'cloud'. On a host WITHOUT a local simulator (Linux, CI, cloud sandbox) it's the default; on macOS, do NOT auto-trigger for a plain 'run on the simulator' - use it only for a cloud/remote/shareable sim, an iOS version they lack, or an agent-driven session. NOT for local sims (expo run:ios, Xcode, Android Studio), EAS Build/Update, web preview, or physical devices.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-simulator/SKILL.md","catch":"Remote iOS/Android sim on EAS cloud, experimental API. Not local sim.","links":{"self":"/api/skills/eas-simulator","html":"/skills/eas-simulator","markdown":"/skills/eas-simulator.md"}},{"id":"eas-update","name":"EAS Update","tagline":"OTA JS/asset updates via expo-updates","when":"OTA JS/asset updates via expo-updates + EAS CLI (`eas update`, channels/branches/runtime). Use when publishing over-the-air JavaScript and asset updates to an Expo app without a new native store binary. Distinct from eas-update-insights (health/adoption of published rollouts, not publish) and eas-app-stores (native store binaries).","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-update/SKILL.md","catch":"EAS service, costs apply (Free plan has update/bandwidth/storage allowances). Distinct from live eas-update-insights (health/adoption, not publish) and eas-app-stores (native store binaries).","links":{"self":"/api/skills/eas-update","html":"/skills/eas-update","markdown":"/skills/eas-update.md"}},{"id":"eas-update-insights","name":"EAS Update Insights","tagline":"Health of published EAS Update rollouts","when":"EAS service (paid). Check the health of published EAS Update: crash rates, install/launch counts, unique users, payload size, and the split between embedded and OTA users per channel. Use when the user asks how an update is performing, whether a rollout is healthy, how many users are on the embedded build vs OTA, or wants to gate CI on update health.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-update-insights/SKILL.md","catch":"Health of published EAS Update rollouts. Idle if you don’t OTA.","links":{"self":"/api/skills/eas-update-insights","html":"/skills/eas-update-insights","markdown":"/skills/eas-update-insights.md"}},{"id":"eas-workflows","name":"EAS Workflows","tagline":".eas/workflows YAML that burns compute minutes","when":"EAS service (paid). Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.","license":"MIT","sourceUrl":"https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-workflows/SKILL.md","catch":".eas/workflows YAML. Each job burns build/compute minutes. False-fire on generic CI.","links":{"self":"/api/skills/eas-workflows","html":"/skills/eas-workflows","markdown":"/skills/eas-workflows.md"}},{"id":"supabase-postgres-best-practices","name":"Supabase Postgres Best Practices","tagline":"Load before any Postgres schema or SQL","when":"Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.","license":"MIT","sourceUrl":"https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md","catch":"Load BEFORE any Postgres schema/SQL. Always-on for SQL, even off Supabase.","links":{"self":"/api/skills/supabase-postgres-best-practices","html":"/skills/supabase-postgres-best-practices","markdown":"/skills/supabase-postgres-best-practices.md"}},{"id":"supabase","name":"Supabase","tagline":"Any Supabase product; changelog-first vendor skill","when":"Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); debugging and troubleshooting errors or unexpected behavior on Supabase projects (HTTP errors, Postgres errors, RLS surprises, permission denied, schema cache issues, timeouts, Edge Function crashes, Realtime drops, Storage failures) and reading or querying logs (Logs Explorer, ClickHouse).","license":"MIT","sourceUrl":"https://github.com/supabase/agent-skills/blob/main/skills/supabase/SKILL.md","catch":"ANY Supabase product. Steals the Postgres skill. Changelog-first; vendor lock.","links":{"self":"/api/skills/supabase","html":"/skills/supabase","markdown":"/skills/supabase.md"}},{"id":"prisma-cli","name":"Prisma CLI","tagline":"ORM CLI: init, generate, migrate, studio","when":"Prisma ORM CLI commands reference covering init, generate, migrate, db, dev, complete, studio, validate, format, debug, and mcp. Use for ORM/database CLI workflows, not the Prisma Platform CLI. Triggers on \"prisma init\", \"prisma generate\", \"prisma migrate\", \"prisma db\", \"prisma complete\", \"prisma studio\", \"prisma mcp\".","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-cli/SKILL.md","catch":"ORM CLI (init/generate/migrate/studio), not Platform CLI.","links":{"self":"/api/skills/prisma-cli","html":"/skills/prisma-cli","markdown":"/skills/prisma-cli.md"}},{"id":"prisma-client-api","name":"Prisma Client API","tagline":"findMany, create, $transaction","when":"Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on \"prisma query\", \"findMany\", \"create\", \"update\", \"delete\", \"$transaction\".","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-client-api/SKILL.md","catch":"findMany/create/$transaction. Idle if you’re not writing Prisma Client.","links":{"self":"/api/skills/prisma-client-api","html":"/skills/prisma-client-api","markdown":"/skills/prisma-client-api.md"}},{"id":"prisma-database-setup","name":"Prisma Database Setup","tagline":"Wire Prisma to Postgres, MySQL, SQLite, Mongo","when":"Guides for configuring Prisma with different database providers (PostgreSQL, MySQL, SQLite, MongoDB, etc.). Use when setting up a new project, changing databases, or troubleshooting connection issues. Triggers on \"configure postgres\", \"connect to mysql\", \"setup mongodb\", \"sqlite setup\".","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-database-setup/SKILL.md","catch":"Wire Prisma to Postgres/MySQL/SQLite/Mongo. Not Prisma Postgres hosting.","links":{"self":"/api/skills/prisma-database-setup","html":"/skills/prisma-database-setup","markdown":"/skills/prisma-database-setup.md"}},{"id":"prisma-driver-adapter-implementation","name":"Prisma Driver Adapter Implementation","tagline":"ORM 7 SQL driver adapters","when":"Required reference for Prisma ORM 7 SQL driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter, Transaction, savepoint, result mapping, or DriverAdapterError behavior. Covers current transaction lifecycle, optional savepoint hooks, original database-error preservation, and verification.","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-driver-adapter-implementation/SKILL.md","catch":"ORM 7 SQL driver adapters. Never-fires for app CRUD.","links":{"self":"/api/skills/prisma-driver-adapter-implementation","html":"/skills/prisma-driver-adapter-implementation","markdown":"/skills/prisma-driver-adapter-implementation.md"}},{"id":"prisma-mongodb-upgrade","name":"Prisma MongoDB Upgrade","tagline":"Mongo on v6 has no v7 path","when":"Decision and migration guide for Prisma ORM MongoDB projects on v6, which have no upgrade path to v7. Use when a MongoDB project asks about upgrading Prisma, when \"upgrade to prisma 7\" comes up in a project with provider = \"mongodb\", or when evaluating a move to Prisma Next. Triggers on \"upgrade prisma mongodb\", \"prisma 7 mongodb\", \"mongodb prisma migration\", \"prisma next mongodb\".","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-mongodb-upgrade/SKILL.md","catch":"Mongo on v6 has no v7 path. Migrate-only.","links":{"self":"/api/skills/prisma-mongodb-upgrade","html":"/skills/prisma-mongodb-upgrade","markdown":"/skills/prisma-mongodb-upgrade.md"}},{"id":"prisma-upgrade-v7","name":"Prisma Upgrade v7","tagline":"v6→v7 breaking changes","when":"Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on \"upgrade to prisma 7\", \"prisma 7 migration\", \"prisma-client generator\", \"driver adapter required\".","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-upgrade-v7/SKILL.md","catch":"v6→v7 breaking changes. Version-gate; will go stale.","links":{"self":"/api/skills/prisma-upgrade-v7","html":"/skills/prisma-upgrade-v7","markdown":"/skills/prisma-upgrade-v7.md"}},{"id":"prisma-postgres","name":"Prisma Postgres","tagline":"Hosted Prisma Postgres, not OSS Postgres","when":"Prisma Postgres setup and operations guidance across Console, create-db CLI, Management API, and Management API SDK. Use when creating Prisma Postgres databases, working in Prisma Console, provisioning with create-db/create-pg/create-postgres, or integrating programmatic provisioning with service tokens or OAuth.","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-postgres/SKILL.md","catch":"Hosted Prisma Postgres. Vendor; Free $0/mo with hard cap (prisma.io/postgres). Not OSS Postgres.","links":{"self":"/api/skills/prisma-postgres","html":"/skills/prisma-postgres","markdown":"/skills/prisma-postgres.md"}},{"id":"prisma-compute","name":"Prisma Compute","tagline":"Prisma Compute deploy, 1M requests/mo free","when":"Prisma Compute deployment and hosting guide. Use whenever the user mentions Prisma Compute, `prisma.compute.ts`, `defineComputeConfig`, deploying or hosting a Prisma app, `@prisma/cli app deploy`, `compute:deploy`, `create-prisma --deploy`, `PRISMA_SERVICE_TOKEN`, Compute auth/workspaces, apps/deployments/build logs/domains, localhost vs `0.0.0.0`, deploy port binding, or framework deploy readiness for Hono, Elysia, Next.js, TanStack Start, Astro, Nuxt, Svelte, Nest, Turborepo, or custom/prebuilt artifacts.","license":"MIT","sourceUrl":"https://github.com/prisma/skills/blob/main/prisma-compute/SKILL.md","catch":"Prisma Compute deploy. Vendor; Free includes 1M requests/mo. Not a generic host.","links":{"self":"/api/skills/prisma-compute","html":"/skills/prisma-compute","markdown":"/skills/prisma-compute.md"}},{"id":"threat-model-generation","name":"Threat Model Generation","tagline":"STRIDE threat model for a repo","when":"Generate a STRIDE-based security threat model for a repository. Use when setting up security monitoring, after architecture changes, or for security audits.","license":"MIT","sourceUrl":"https://github.com/factory-ai/skills/blob/main/skills/threat-model-generation/SKILL.md","catch":"STRIDE doc; not sentry security-review.","links":{"self":"/api/skills/threat-model-generation","html":"/skills/threat-model-generation","markdown":"/skills/threat-model-generation.md"}},{"id":"firecrawl-agent","name":"Firecrawl Agent","tagline":"Multi-page schema extract via Firecrawl agent","when":"Autonomous multi-page extraction into structured JSON. Use when the user wants website data matching a schema — pricing tiers, product listings — beyond a single-page scrape.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-agent/SKILL.md","catch":"multi-page schema extract; credits; not a generic crawler. Self-host via FIRECRAWL_API_URL is the free path; cloud needs a key.","links":{"self":"/api/skills/firecrawl-agent","html":"/skills/firecrawl-agent","markdown":"/skills/firecrawl-agent.md"}},{"id":"firecrawl-crawl","name":"Firecrawl Crawl","tagline":"Bulk crawl; no keyless free tier","when":"Bulk-extract many pages from one site or section. Use for \"crawl\", \"everything under /docs\", or content spanning linked pages.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-crawl/SKILL.md","catch":"LOUD: skill text: crawl has no keyless free tier; credits per page; auth required.","links":{"self":"/api/skills/firecrawl-crawl","html":"/skills/firecrawl-crawl","markdown":"/skills/firecrawl-crawl.md"}},{"id":"firecrawl-build-scrape","name":"Firecrawl Build Scrape","tagline":"One-URL /scrape in app code","when":"Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/build/firecrawl-build-scrape/SKILL.md","catch":"one-URL scrape in app code. Self-host option. Not crawl.","links":{"self":"/api/skills/firecrawl-build-scrape","html":"/skills/firecrawl-build-scrape","markdown":"/skills/firecrawl-build-scrape.md"}},{"id":"firecrawl-build-search","name":"Firecrawl Build Search","tagline":"Firecrawl /search in product code","when":"Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/build/firecrawl-build-search/SKILL.md","catch":"Firecrawl /search; not a generic web-search skill.","links":{"self":"/api/skills/firecrawl-build-search","html":"/skills/firecrawl-build-search","markdown":"/skills/firecrawl-build-search.md"}},{"id":"firecrawl-build-interact","name":"Firecrawl Build Interact","tagline":"Clicks and forms after scrape","when":"Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/build/firecrawl-build-interact/SKILL.md","catch":"clicks/forms after scrape. Overlaps shipped webapp-testing and Browserbase browser.","links":{"self":"/api/skills/firecrawl-build-interact","html":"/skills/firecrawl-build-interact","markdown":"/skills/firecrawl-build-interact.md"}},{"id":"huggingface-papers","name":"Hugging Face Papers","tagline":"HF/arXiv URL to markdown","when":"Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-papers/SKILL.md","catch":"HF/arXiv URL → markdown. Papers only.","links":{"self":"/api/skills/huggingface-papers","html":"/skills/huggingface-papers","markdown":"/skills/huggingface-papers.md"}},{"id":"browser","name":"Browser","tagline":"NL browse CLI; local Chrome or Browserbase","when":"Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.","license":"MIT (frontmatter; no LICENSE file)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/browser/SKILL.md","catch":"NL browse CLI. Local Chrome is the free path; remote Browserbase needs API key. Loud: no repo LICENSE (frontmatter MIT only).","links":{"self":"/api/skills/browser","html":"/skills/browser","markdown":"/skills/browser.md"}},{"id":"browser-trace","name":"Browser Trace","tagline":"CDP/screenshot debug of a failed browse","when":"Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.","license":"MIT (frontmatter; no LICENSE file)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/browser-trace/SKILL.md","catch":"CDP/screenshot debug of a failed browse. Dead without browser.","links":{"self":"/api/skills/browser-trace","html":"/skills/browser-trace","markdown":"/skills/browser-trace.md"}},{"id":"browser-to-api","name":"Browser to API","tagline":"Trace to OpenAPI 3.1 from XHR","when":"Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover/extract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR/fetch surface for client integration.","license":"MIT (frontmatter; no LICENSE file)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/browser-to-api/SKILL.md","catch":"trace → OpenAPI 3.1 from XHR. Needs browser-trace first; not an exploit skill.","links":{"self":"/api/skills/browser-to-api","html":"/skills/browser-to-api","markdown":"/skills/browser-to-api.md"}},{"id":"transformers-js","name":"Transformers.js","tagline":"Transformers.js in browser and Node","when":"Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/transformers-js/SKILL.md","catch":"Transformers.js in browser/Node. Weight downloads and RAM are the limit.","links":{"self":"/api/skills/transformers-js","html":"/skills/transformers-js","markdown":"/skills/transformers-js.md"}},{"id":"huggingface-local-models","name":"Hugging Face Local Models","tagline":"GGUF + llama.cpp on CPU/Metal/CUDA/ROCm","when":"Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-local-models/SKILL.md","catch":"GGUF + llama.cpp on CPU/Metal/CUDA/ROCm. Not a cloud-Jobs trainer.","links":{"self":"/api/skills/huggingface-local-models","html":"/skills/huggingface-local-models","markdown":"/skills/huggingface-local-models.md"}},{"id":"huggingface-datasets","name":"Hugging Face Datasets","tagline":"Hub Dataset Viewer API","when":"Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-datasets/SKILL.md","catch":"Hub Dataset Viewer API. Not local datasets training prep. (frontmatter nonstandard; file 200.)","links":{"self":"/api/skills/huggingface-datasets","html":"/skills/huggingface-datasets","markdown":"/skills/huggingface-datasets.md"}},{"id":"huggingface-gradio","name":"Hugging Face Gradio","tagline":"Gradio apps in Python","when":"Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-gradio/SKILL.md","catch":"Gradio apps only. Not a general frontend skill.","links":{"self":"/api/skills/huggingface-gradio","html":"/skills/huggingface-gradio","markdown":"/skills/huggingface-gradio.md"}},{"id":"huggingface-trackio","name":"Hugging Face Trackio","tagline":"Trackio metrics, not W&B","when":"Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-trackio/SKILL.md","catch":"Trackio metrics. Dead if the project uses W&B/MLflow.","links":{"self":"/api/skills/huggingface-trackio","html":"/skills/huggingface-trackio","markdown":"/skills/huggingface-trackio.md"}},{"id":"huggingface-community-evals","name":"Hugging Face Community Evals","tagline":"Local inspect-ai and lighteval","when":"Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-community-evals/SKILL.md","catch":"local inspect-ai/lighteval. Not HF Jobs.","links":{"self":"/api/skills/huggingface-community-evals","html":"/skills/huggingface-community-evals","markdown":"/skills/huggingface-community-evals.md"}},{"id":"huggingface-paper-publisher","name":"Hugging Face Paper Publisher","tagline":"Create and claim HF paper pages","when":"Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-paper-publisher/SKILL.md","catch":"create/claim HF paper pages. Distinct from huggingface-papers (reader).","links":{"self":"/api/skills/huggingface-paper-publisher","html":"/skills/huggingface-paper-publisher","markdown":"/skills/huggingface-paper-publisher.md"}},{"id":"huggingface-vision-trainer","name":"Hugging Face Vision Trainer","tagline":"Detection/SAM on HF Jobs GPUs","when":"Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-vision-trainer/SKILL.md","catch":"detection/SAM on HF Jobs GPUs. Loud Catch: cloud-GPU costs apply.","links":{"self":"/api/skills/huggingface-vision-trainer","html":"/skills/huggingface-vision-trainer","markdown":"/skills/huggingface-vision-trainer.md"}},{"id":"playwright","name":"Playwright","tagline":"playwright-cli from the terminal","when":"Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/playwright/SKILL.md","catch":"playwright-cli from the terminal. Twin of shipped webapp-testing (CLI wrapper, not the library).","links":{"self":"/api/skills/playwright","html":"/skills/playwright","markdown":"/skills/playwright.md"}},{"id":"jupyter-notebook","name":"Jupyter Notebook","tagline":".ipynb only, not a Python app skill","when":"Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/jupyter-notebook/SKILL.md","catch":".ipynb only. Not a Python app skill.","links":{"self":"/api/skills/jupyter-notebook","html":"/skills/jupyter-notebook","markdown":"/skills/jupyter-notebook.md"}},{"id":"gh-fix-ci","name":"GH Fix CI","tagline":"Failing Actions on the current PR","when":"Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/gh-fix-ci/SKILL.md","catch":"failing Actions on the current PR; implement only after explicit approval. Buildkite out of scope.","links":{"self":"/api/skills/gh-fix-ci","html":"/skills/gh-fix-ci","markdown":"/skills/gh-fix-ci.md"}},{"id":"gh-address-comments","name":"GH Address Comments","tagline":"Review comments on the current-branch PR","when":"Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/gh-address-comments/SKILL.md","catch":"review comments on the current-branch PR via gh. Needs gh auth.","links":{"self":"/api/skills/gh-address-comments","html":"/skills/gh-address-comments","markdown":"/skills/gh-address-comments.md"}},{"id":"yeet","name":"Yeet","tagline":"Stage, commit, push, and open a PR","when":"Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/yeet/SKILL.md","catch":"stage+commit+push+PR in one flow. Loud: only when the user explicitly asks; dangerous if it false-fires.","links":{"self":"/api/skills/yeet","html":"/skills/yeet","markdown":"/skills/yeet.md"}},{"id":"screenshot","name":"Screenshot","tagline":"OS-level capture, not web page shots","when":"Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/screenshot/SKILL.md","catch":"OS-level capture. Not web page shots.","links":{"self":"/api/skills/screenshot","html":"/skills/screenshot","markdown":"/skills/screenshot.md"}},{"id":"openai-docs","name":"OpenAI Docs","tagline":"Current OpenAI/Codex docs; twin of claude-api","when":"Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/openai-docs/SKILL.md","catch":"current OpenAI/Codex docs. Loud vendor; twin of claude-api.","links":{"self":"/api/skills/openai-docs","html":"/skills/openai-docs","markdown":"/skills/openai-docs.md"}},{"id":"netlify-deploy","name":"Netlify Deploy","tagline":"npx netlify; Netlify says build free","when":"Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/netlify-deploy/SKILL.md","catch":"npx netlify. Vendor; netlify.com/pricing: “Build free.”","links":{"self":"/api/skills/netlify-deploy","html":"/skills/netlify-deploy","markdown":"/skills/netlify-deploy.md"}},{"id":"render-deploy","name":"Render Deploy","tagline":"render.yaml; Render says deploy for free","when":"Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/render-deploy/SKILL.md","catch":"render.yaml. Vendor; render.com/pricing: “Deploy for free.”","links":{"self":"/api/skills/render-deploy","html":"/skills/render-deploy","markdown":"/skills/render-deploy.md"}},{"id":"linear","name":"Linear","tagline":"Issues via Linear; Free $0, needs auth","when":"Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/linear/SKILL.md","catch":"issues via Linear. Vendor; linear.app/pricing Free $0. Dead without Linear auth.","links":{"self":"/api/skills/linear","html":"/skills/linear","markdown":"/skills/linear.md"}},{"id":"notion-knowledge-capture","name":"Notion Knowledge Capture","tagline":"Chats into a Notion wiki or how-to","when":"Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.","license":"MIT","sourceUrl":"https://github.com/openai/plugins/blob/main/plugins/notion/skills/notion-knowledge-capture/SKILL.md","catch":"chats → Notion wiki/how-to. Vendor; notion.so/pricing has a Free plan. Dead without Notion MCP.","links":{"self":"/api/skills/notion-knowledge-capture","html":"/skills/notion-knowledge-capture","markdown":"/skills/notion-knowledge-capture.md"}},{"id":"upstash-redis-start","name":"Upstash Redis Start","tagline":"Scratch Redis, 72h, no signup","when":"Provision a zero-config, no-signup, temporary Upstash Redis database for an AI agent with a single POST to https://upstash.com/start-redis, with no account, API key, or SDK setup required. Use when an agent needs scratch Redis right now and the user has not provided credentials, for short-term memory across tool calls, conversation history, a sub-agent work queue, ranked recall, or a quick prototype or demo. Covers idempotent creation and re-fetching credentials, calling the database through the body-style REST API or the official SDKs, and telling the user how to claim it. The database lives 3 days unless the user claims it; not for production data, PII, or secrets.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-redis-start/SKILL.md","catch":"scratch Redis, no signup. Temporary; not production. Free path: start-redis 72h no-signup.","links":{"self":"/api/skills/upstash-redis-start","html":"/skills/upstash-redis-start","markdown":"/skills/upstash-redis-start.md"}},{"id":"upstash-redis-js","name":"Upstash Redis JS","tagline":"@upstash/redis HTTP client, not ioredis","when":"Work with the @upstash/redis TypeScript/JavaScript SDK, a serverless HTTP-based Redis client for Next.js, Vercel, Cloudflare Workers, edge runtimes, and Node.js. Use when adding a cache (cache-aside, write-through, TTL and expiration strategies), session storage and user sessions, a key-value store, leaderboards and rankings with sorted sets, counters, distributed locks, queues with lists, streams and consumer groups, JSON documents, pipelines and MULTI/EXEC transactions, Lua scripting, read replicas, or full-text search, typo-tolerant search, facets, and aggregations with Upstash Redis Search (different from regular FT.SEARCH; also available for TCP clients via @upstash/search-redis and @upstash/search-ioredis). Also use when migrating from ioredis or node-redis, when a Redis connection is needed from a serverless function without connection pooling, when integrating @upstash/ratelimit, or when the user says Redis cache, KV store, session store, serverless Redis, or Upstash Redis. Supports automatic serialization/deserialization of JavaScript types.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-redis-js/SKILL.md","catch":"@upstash/redis HTTP client. Not ioredis/node-redis. Free $0 on upstash.com/pricing.","links":{"self":"/api/skills/upstash-redis-js","html":"/skills/upstash-redis-js","markdown":"/skills/upstash-redis-js.md"}},{"id":"upstash-ratelimit-js","name":"Upstash Ratelimit JS","tagline":"Rate limit on top of Upstash Redis","when":"Rate limiting for serverless and edge apps with the @upstash/ratelimit TypeScript/JavaScript SDK backed by Upstash Redis. Use when adding a rate limiter or throttling to an API route, Next.js middleware, Vercel Edge, Cloudflare Workers, or any HTTP endpoint; returning 429 Too Many Requests; choosing between fixed window, sliding window, and token bucket algorithms; limiting per user, IP, API key, or tenant with prefixes and custom keys; protecting login, signup, form, or AI endpoints from abuse, bots, and brute force; using deny lists, ephemeral caching, analytics, timeouts, and multi-region rate limits; or estimating the Redis command cost of rate limiting. Also use when the user says rate limit, rate-limiting, throttle, quota, request limits, or traffic protection.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-ratelimit-js/SKILL.md","catch":"needs Upstash Redis underneath. Free $0 on upstash.com/pricing.","links":{"self":"/api/skills/upstash-ratelimit-js","html":"/skills/upstash-ratelimit-js","markdown":"/skills/upstash-ratelimit-js.md"}},{"id":"upstash-qstash-js","name":"Upstash QStash JS","tagline":"HTTP queue and schedules on QStash","when":"Work with the @upstash/qstash TypeScript/JavaScript SDK, an HTTP-based message queue, task scheduler, and background job system for serverless and edge runtimes (Next.js, Vercel, Cloudflare Workers, Deno, Node.js). Use when publishing messages to HTTP endpoints or URL groups, running background jobs without a long-running worker process, scheduling with cron expressions, delaying messages, building FIFO queues with parallelism and flow control, configuring retries and callbacks, handling a dead letter queue (DLQ), deduplicating messages, fanning out to multiple endpoints, verifying QStash webhook signatures (Next.js App Router, Pages Router, and Edge Runtime), running a local QStash dev server, or migrating regions. Also use when the user asks for a serverless cron job, async task queue, job scheduler, delayed delivery, webhook delivery with retries, or event-driven messaging between services.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-qstash-js/SKILL.md","catch":"HTTP queue/schedules. Vendor; Free $0 on pricing.","links":{"self":"/api/skills/upstash-qstash-js","html":"/skills/upstash-qstash-js","markdown":"/skills/upstash-qstash-js.md"}},{"id":"upstash-workflow-js","name":"Upstash Workflow JS","tagline":"Durable workflows on QStash","when":"Work with the @upstash/workflow TypeScript/JavaScript SDK for durable, long-running workflows in serverless functions, multi-step processes that survive timeouts, retries, and restarts (built on QStash). Use when defining a workflow endpoint with serve(), running steps with context.run, sleeping for minutes to days without holding a function open, calling external APIs with context.call, waiting for an external event or webhook, invoking other workflows, configuring retries, failure callbacks, and a DLQ, controlling concurrency, rate, and parallelism, triggering, cancelling, or inspecting runs with the Workflow client, building AI agents and orchestrators, human-in-the-loop approvals, realtime updates, local development with the QStash dev server, adding middleware, or migrating workflows safely. Also use when the user asks for durable execution, step functions, saga or orchestration patterns, background jobs with checkpoints, or long-running tasks on Vercel, Next.js, Cloudflare Workers, or other serverless platforms.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-workflow-js/SKILL.md","catch":"durable workflows on QStash. Distinct from qstash-js, not a twin dump.","links":{"self":"/api/skills/upstash-workflow-js","html":"/skills/upstash-workflow-js","markdown":"/skills/upstash-workflow-js.md"}},{"id":"upstash-vector-js","name":"Upstash Vector JS","tagline":"Upstash Vector, not pgvector","when":"Work with the @upstash/vector TypeScript/JavaScript SDK, a serverless vector database for embeddings, similarity search, semantic search, and RAG (retrieval-augmented generation). Use when upserting, querying, fetching, ranging, or deleting vectors, upserting raw text against an index with a built-in embedding model, choosing dense, sparse, or hybrid indexes, filtering by metadata, organizing data with namespaces, running resumable queries, or connecting Upstash Vector to an AI or LLM application. Also use when the user asks for a vector store, vector search, nearest-neighbor or kNN search, embeddings storage, semantic cache, recommendations or similarity features, or a hosted vector index that needs no infrastructure.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-vector-js/SKILL.md","catch":"not pgvector. Free $0 on upstash.com/pricing.","links":{"self":"/api/skills/upstash-vector-js","html":"/skills/upstash-vector-js","markdown":"/skills/upstash-vector-js.md"}},{"id":"upstash-search-js","name":"Upstash Search JS","tagline":"Upstash Search vendor SDK","when":"Work with the @upstash/search TypeScript/JavaScript SDK, a serverless full-text and semantic search database with built-in reranking. Use when adding search to an app or site, creating a search index, upserting documents with searchable content and filterable metadata, running keyword, semantic, or hybrid search queries, reranking results, filtering with SQL-like or structured filter syntax, paginating with range, fetching or deleting documents, resetting an index, or checking index info. Also use when the user asks for site search, product, document, or knowledge-base search, or a managed search service that needs no cluster to run.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-search-js/SKILL.md","catch":"Upstash Search vendor. Free $0 on upstash.com/pricing.","links":{"self":"/api/skills/upstash-search-js","html":"/skills/upstash-search-js","markdown":"/skills/upstash-search-js.md"}},{"id":"upstash-cli","name":"Upstash CLI","tagline":"upstash CLI; needs API token","when":"Run the Upstash CLI (`upstash`) against the Upstash Developer API for Redis, Vector, Search, QStash, and teams, with non-interactive commands and JSON output for scripts, CI, and agents. Use when creating, listing, renaming, or deleting Redis databases, changing plans, regions, TLS, eviction, auto-upgrade, or budgets, managing backups, running Redis commands with `upstash redis exec`, creating or inspecting Vector and Search indexes, managing QStash instances and tokens, managing team members, reading usage stats, or automating any Upstash account operation from the terminal. Also use when the user asks how to provision or manage Upstash resources without the console.","license":"MIT","sourceUrl":"https://github.com/upstash/skills/blob/main/skills/upstash-cli/SKILL.md","catch":"needs API token; CI/agent oriented.","links":{"self":"/api/skills/upstash-cli","html":"/skills/upstash-cli","markdown":"/skills/upstash-cli.md"}},{"id":"planetscale-pscale-cli-automation","name":"PlanetScale pscale CLI Automation","tagline":"Headless pscale with --format json","when":"Use the PlanetScale CLI (pscale) from automated agents with --format json, auth check, pscale sql, and per-command --force. Run before other PlanetScale skills when driving pscale directly. Use when the user asks to automate pscale, run CLI commands headless, or verify pscale auth from an agent.","license":"MIT","sourceUrl":"https://github.com/planetscale/skills/blob/main/planetscale-pscale-cli-automation/SKILL.md","catch":"LOUD: planetscale.com/pricing has no verified $0 hobby (calculator from ~$15; “first 10 GB free” is storage add-on language, not a catalog free tier).","links":{"self":"/api/skills/planetscale-pscale-cli-automation","html":"/skills/planetscale-pscale-cli-automation","markdown":"/skills/planetscale-pscale-cli-automation.md"}},{"id":"planetscale-postgres-safety-review","name":"PlanetScale Postgres Safety Review","tagline":"PS Postgres only; not the Supabase skill","when":"Review PlanetScale Postgres for Traffic Control, query tags, roles, pg_strict, backups/PITR, private connectivity, webhooks, branches, and safe agent operation.","license":"MIT","sourceUrl":"https://github.com/planetscale/skills/blob/main/planetscale-postgres-safety-review/SKILL.md","catch":"PS Postgres only; not the Supabase Postgres skill. LOUD: no verified $0 PlanetScale hobby.","links":{"self":"/api/skills/planetscale-postgres-safety-review","html":"/skills/planetscale-postgres-safety-review","markdown":"/skills/planetscale-postgres-safety-review.md"}},{"id":"planetscale-vitess-safety-review","name":"PlanetScale Vitess Safety Review","tagline":"Vitess branch safety review","when":"Review a PlanetScale Vitess database for safe migrations, deploy requests, schema recommendations, Insights, webhooks, and operational safety.","license":"MIT","sourceUrl":"https://github.com/planetscale/skills/blob/main/planetscale-vitess-safety-review/SKILL.md","catch":"Vitess branch only. LOUD: no verified $0 PlanetScale hobby.","links":{"self":"/api/skills/planetscale-vitess-safety-review","html":"/skills/planetscale-vitess-safety-review","markdown":"/skills/planetscale-vitess-safety-review.md"}},{"id":"planetscale-query-insights-and-tags","name":"PlanetScale Query Insights and Tags","tagline":"PlanetScale query insights and tags","when":"Use PlanetScale Insights and SQLCommenter-style query tags to attribute database load, identify risky queries, and prepare safe Traffic Control or schema recommendations.","license":"MIT","sourceUrl":"https://github.com/planetscale/skills/blob/main/planetscale-query-insights-and-tags/SKILL.md","catch":"PlanetScale query insights/tags. LOUD: no verified $0 PlanetScale hobby.","links":{"self":"/api/skills/planetscale-query-insights-and-tags","html":"/skills/planetscale-query-insights-and-tags","markdown":"/skills/planetscale-query-insights-and-tags.md"}},{"id":"planetscale-schema-recommendations-agent-loop","name":"PlanetScale Schema Recommendations Agent Loop","tagline":"Triage PS schema recs; does not apply prod","when":"Safely triage PlanetScale schema recommendations and turn them into reviewed branches, migrations, issues, or pull requests without applying production changes.","license":"MIT","sourceUrl":"https://github.com/planetscale/skills/blob/main/planetscale-schema-recommendations-agent-loop/SKILL.md","catch":"never-fires without PS schema recs; does not apply prod. LOUD: no verified $0 PlanetScale hobby.","links":{"self":"/api/skills/planetscale-schema-recommendations-agent-loop","html":"/skills/planetscale-schema-recommendations-agent-loop","markdown":"/skills/planetscale-schema-recommendations-agent-loop.md"}},{"id":"planetscale-mcp-agent-operating-model","name":"PlanetScale MCP Agent Operating Model","tagline":"PS MCP policy; dead without PS MCP","when":"Configure safe agent behavior around PlanetScale MCP, Insights, schema recommendations, and repository work without autonomous production mutation.","license":"MIT","sourceUrl":"https://github.com/planetscale/skills/blob/main/planetscale-mcp-agent-operating-model/SKILL.md","catch":"policy; dead without PS MCP. LOUD: no verified $0 PlanetScale hobby.","links":{"self":"/api/skills/planetscale-mcp-agent-operating-model","html":"/skills/planetscale-mcp-agent-operating-model","markdown":"/skills/planetscale-mcp-agent-operating-model.md"}},{"id":"workos","name":"WorkOS","tagline":"WorkOS auth; Free $0/mo, dead without WorkOS","when":"Use when the user asks for a WorkOS docs URL, term, or dashboard field (Sign-in endpoint, initiate_login_uri, Redirect URI, `WORKOS_*` env vars), or is implementing, debugging, or migrating WorkOS — AuthKit, SSO/SAML, Directory Sync, RBAC, FGA, MFA, Vault, Audit Logs, Admin Portal, Pipes (Connected Apps), Feature Flags, Radar (bot/fraud detection), webhooks, Custom Domains, running the `workos` CLI in agent or sandbox sessions (`WORKOS_MODE`, `workos doctor`), or migrating from Auth0, Clerk, Cognito, Firebase, Supabase, Stytch, Descope, or Better Auth. Also triggers on @workos-inc/* imports.","license":"MIT","sourceUrl":"https://github.com/workos/skills/blob/main/plugins/workos/skills/workos/SKILL.md","catch":"WorkOS auth. Vendor; workos.com/pricing Free $0/mo. Dead without WorkOS.","links":{"self":"/api/skills/workos","html":"/skills/workos","markdown":"/skills/workos.md"}},{"id":"aspnet-core","name":"ASP.NET Core","tagline":".NET-only ASP.NET Core, Blazor, Minimal APIs","when":"Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/aspnet-core/SKILL.md","catch":".NET-only. Never-fires outside ASP.NET Core / Blazor / Minimal APIs.","links":{"self":"/api/skills/aspnet-core","html":"/skills/aspnet-core","markdown":"/skills/aspnet-core.md"}},{"id":"chatgpt-apps","name":"ChatGPT Apps","tagline":"ChatGPT Apps SDK with MCP widget","when":"Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/chatgpt-apps/SKILL.md","catch":"ChatGPT Apps SDK (MCP + widget). Not generic MCP — pulls you into ChatGPT Apps.","links":{"self":"/api/skills/chatgpt-apps","html":"/skills/chatgpt-apps","markdown":"/skills/chatgpt-apps.md"}},{"id":"cli-creator","name":"CLI Creator","tagline":"Codex companion CLI from OpenAPI or curl","when":"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.","license":"Apache-2.0","sourceUrl":"https://github.com/openai/skills/blob/main/skills/.curated/cli-creator/SKILL.md","catch":"Codex companion CLI from OpenAPI/curl. Not a product feature.","links":{"self":"/api/skills/cli-creator","html":"/skills/cli-creator","markdown":"/skills/cli-creator.md"}},{"id":"multi-stage-dockerfile","name":"Multi-Stage Dockerfile","tagline":"Dockerfile-only multi-stage images","when":"Create optimized multi-stage Dockerfiles for any language or framework","license":"MIT","sourceUrl":"https://github.com/github/awesome-copilot/blob/main/skills/multi-stage-dockerfile/SKILL.md","catch":"Dockerfile-only. Will rewrite the image even when you asked for app code.","links":{"self":"/api/skills/multi-stage-dockerfile","html":"/skills/multi-stage-dockerfile","markdown":"/skills/multi-stage-dockerfile.md"}},{"id":"mcp-security-audit","name":"MCP Security Audit","tagline":"Audit .mcp.json, not security-review","when":"Audit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: reviewing .mcp.json files for security risks; checking MCP server args for hardcoded secrets or shell injection patterns; validating that MCP servers use pinned versions (not @latest); detecting unpinned dependencies in MCP server configurations; auditing which MCP servers a project registers and whether they're on an approved list; checking for environment variable usage vs. hardcoded credentials in MCP configs; any request like \"is my MCP config secure?\", \"audit my MCP servers\", or \"check .mcp.json\".","license":"MIT","sourceUrl":"https://github.com/github/awesome-copilot/blob/main/skills/mcp-security-audit/SKILL.md","catch":"Audits .mcp.json for secrets, shell injection, unpinned @latest. Config-only — not security-review.","links":{"self":"/api/skills/mcp-security-audit","html":"/skills/mcp-security-audit","markdown":"/skills/mcp-security-audit.md"}},{"id":"openapi-to-application-code","name":"OpenAPI to Application Code","tagline":"Codegen a whole app from an OpenAPI spec","when":"Generate a complete, production-ready application from an OpenAPI specification","license":"MIT","sourceUrl":"https://github.com/github/awesome-copilot/blob/main/skills/openapi-to-application-code/SKILL.md","catch":"Loud: codegen mega-skill; will invent a whole production app from a spec.","links":{"self":"/api/skills/openapi-to-application-code","html":"/skills/openapi-to-application-code","markdown":"/skills/openapi-to-application-code.md"}},{"id":"safe-browser","name":"Safe Browser","tagline":"Local domain-allowlisted Claude Agent SDK browser","when":"Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.","license":"MIT (frontmatter; repo LICENSE 404)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/safe-browser/SKILL.md","catch":"Local domain-allowlisted browser (Claude Agent SDK). Not Browserbase cloud. Loud: undeclared-repo LICENSE.","links":{"self":"/api/skills/safe-browser","html":"/skills/safe-browser","markdown":"/skills/safe-browser.md"}},{"id":"functions","name":"Browserbase Functions","tagline":"Scheduled or webhook Browserbase cloud browser jobs","when":"Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions.","license":"MIT (frontmatter; repo LICENSE 404)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/functions/SKILL.md","catch":"Browserbase Functions — scheduled/webhook cloud browser jobs. Loud: paid product path.","links":{"self":"/api/skills/functions","html":"/skills/functions","markdown":"/skills/functions.md"}},{"id":"firecrawl-map","name":"Firecrawl Map","tagline":"URL list/filter. Discovery only; not extract","when":"Discover and list a site's URLs, with search filtering. Use for \"map the site\" or \"find the URL for\" requests — when the user knows the site but not the exact page, or wants site structure.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-map/SKILL.md","catch":"URL list/filter. Discovery only; not extract.","links":{"self":"/api/skills/firecrawl-map","html":"/skills/firecrawl-map","markdown":"/skills/firecrawl-map.md"}},{"id":"firecrawl-download","name":"Firecrawl Download","tagline":"Bulk local markdown and screenshots","when":"Save a site or section as local files (markdown, screenshots). Use for \"download the site\", offline docs, or a local copy for reference.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-download/SKILL.md","catch":"bulk local markdown/screenshots. Loud: credit-heavy.","links":{"self":"/api/skills/firecrawl-download","html":"/skills/firecrawl-download","markdown":"/skills/firecrawl-download.md"}},{"id":"firecrawl-monitor","name":"Firecrawl Monitor","tagline":"Webhook/email watches; recurring paid path","when":"Alert by webhook/email on web changes — use for \"monitor/watch/track/alert me when\": recurring checks on known URLs (prefer over repeated one-off scrapes) or web-wide watches for new results (queries + goal).","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-monitor/SKILL.md","catch":"webhook/email watches. Loud: recurring paid path.","links":{"self":"/api/skills/firecrawl-monitor","html":"/skills/firecrawl-monitor","markdown":"/skills/firecrawl-monitor.md"}},{"id":"instrument-integration","name":"Instrument Integration","tagline":"PostHog SDK wiring. Free, not a trial","when":"Add PostHog SDK integration to your application. Use when setting up PostHog for the first time or reviewing PRs that need PostHog initialization. Covers SDK installation, provider setup, and basic configuration for any framework.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/instrument-integration/SKILL.md","catch":"PostHog SDK wiring. Free on posthog.com/pricing (not a trial).","links":{"self":"/api/skills/instrument-integration","html":"/skills/instrument-integration","markdown":"/skills/instrument-integration.md"}},{"id":"instrument-product-analytics","name":"Instrument Product Analytics","tagline":"PostHog product analytics events","when":"Add PostHog product analytics events to track user behavior. Use after implementing new features or reviewing PRs to ensure meaningful user actions are captured. Also handles initial PostHog SDK setup if not yet installed.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/instrument-product-analytics/SKILL.md","catch":"PostHog product analytics events. Free tier; not a trial.","links":{"self":"/api/skills/instrument-product-analytics","html":"/skills/instrument-product-analytics","markdown":"/skills/instrument-product-analytics.md"}},{"id":"instrument-feature-flags","name":"Instrument Feature Flags","tagline":"PostHog feature flags. Free tier","when":"Add PostHog feature flags to gate new functionality. Use after implementing features or reviewing PRs to ensure safe rollouts with feature flag controls. Also handles initial PostHog SDK setup if not yet installed.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/instrument-feature-flags/SKILL.md","catch":"PostHog feature flags. Free tier; not a trial.","links":{"self":"/api/skills/instrument-feature-flags","html":"/skills/instrument-feature-flags","markdown":"/skills/instrument-feature-flags.md"}},{"id":"instrument-llm-analytics","name":"Instrument LLM Analytics","tagline":"PostHog LLM analytics. Free tier","when":"Add PostHog LLM analytics to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/instrument-llm-analytics/SKILL.md","catch":"PostHog LLM analytics. Free tier; not a trial.","links":{"self":"/api/skills/instrument-llm-analytics","html":"/skills/instrument-llm-analytics","markdown":"/skills/instrument-llm-analytics.md"}},{"id":"liveblocks-best-practices","name":"Liveblocks Best Practices","tagline":"Liveblocks collab. Free on liveblocks.io/pricing","when":"Use this skill when building, debugging, or answering questions about Liveblocks. Liveblocks gives you the building blocks and infrastructure to enable people and AI to work together inside your app, powering realtime collaboration. Liveblocks features include collaboration, rooms, organizations, workspaces, comments, composer, threads, notifications, multiplayer, conflict resolution, realtime presence, avatar stacks, AI collaborators, AI agents, text editors, Tiptap, BlockNote, Lexical, React Flow, Chat SDK. Common components include AiChat, Thread, InboxNotification, Composer, Toolbar (for Lexical Tiptap), FloatingToolbar, FloatingComposer, FloatingThreads, AnchoredThreads. Common hooks include useThreads, useStorage, useMutation, useOthers, useInboxNotifications, useAiChats. Common issues are related to authentication (ID tokens vs access tokens), permissions, room limits, connection errors, user info.","license":"Apache-2.0","sourceUrl":"https://github.com/liveblocks/skills/blob/main/skills/liveblocks-best-practices/SKILL.md","catch":"Liveblocks collab. Free on liveblocks.io/pricing; no CC.","links":{"self":"/api/skills/liveblocks-best-practices","html":"/skills/liveblocks-best-practices","markdown":"/skills/liveblocks-best-practices.md"}},{"id":"yjs-best-practices","name":"Yjs Best Practices","tagline":"Yjs library, not Liveblocks-specific","when":"Use this skill when implementing or debugging Yjs features. It helps with Yjs import issues, subdocuments, `YKeyValue`, `Y.Map`, and experimental V2 encoding.","license":"Apache-2.0","sourceUrl":"https://github.com/liveblocks/skills/blob/main/skills/yjs-best-practices/SKILL.md","catch":"Yjs library, not Liveblocks-specific.","links":{"self":"/api/skills/yjs-best-practices","html":"/skills/yjs-best-practices","markdown":"/skills/yjs-best-practices.md"}},{"id":"stripe-best-practices","name":"Stripe Best Practices","tagline":"Stripe account exists; processing fees apply","when":"Guides Stripe integration decisions across API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax, automatic_tax, product tax codes), Treasury financial accounts, integration options (Checkout, Payment Element), migrating from deprecated Stripe APIs, and security best practices (API key management, restricted keys, webhooks, OAuth). Use when building, modifying, or reviewing any Stripe integration, including accepting payments, building marketplaces, integrating Stripe, processing payments, setting up subscriptions, collecting sales tax, VAT, or GST, creating connected accounts, or implementing secure key handling.","license":"MIT","sourceUrl":"https://github.com/stripe/ai/blob/main/skills/stripe-best-practices/SKILL.md","catch":"Loud: Stripe account exists; processing fees apply. Toolkit MIT.","links":{"self":"/api/skills/stripe-best-practices","html":"/skills/stripe-best-practices","markdown":"/skills/stripe-best-practices.md"}},{"id":"stripe-docs","name":"Stripe Docs","tagline":"Stripe docs lookup. Processing fees apply","when":"Use when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any docs.stripe.com content.","license":"MIT","sourceUrl":"https://github.com/stripe/ai/blob/main/skills/stripe-docs/SKILL.md","catch":"Stripe docs lookup. Loud: processing fees apply.","links":{"self":"/api/skills/stripe-docs","html":"/skills/stripe-docs","markdown":"/skills/stripe-docs.md"}},{"id":"upgrade-stripe","name":"Upgrade Stripe","tagline":"Stripe API/SDK upgrade path","when":"Guide for upgrading Stripe API versions and SDKs","license":"MIT","sourceUrl":"https://github.com/stripe/ai/blob/main/skills/upgrade-stripe/SKILL.md","catch":"Stripe API/SDK upgrade path. Loud: processing fees apply.","links":{"self":"/api/skills/upgrade-stripe","html":"/skills/upgrade-stripe","markdown":"/skills/upgrade-stripe.md"}},{"id":"migrate-ai-sdk-v6-to-v7","name":"Migrate AI SDK v6 to v7","tagline":"Vercel AI SDK v6→v7. Version-gate; will stale","when":"Migrate applications from AI SDK 6.x to AI SDK 7.0. Use when upgrading Vercel AI SDK packages, fixing v7 migration errors, or when the user mentions AI SDK v6, v7, upgrade, migration, breaking changes, system to instructions, fullStream, telemetry, tool context, or finalStep.","license":"Apache-2.0","sourceUrl":"https://github.com/vercel/ai/blob/main/skills/migrate-ai-sdk-v6-to-v7/SKILL.md","catch":"Vercel AI SDK v6→v7. Version-gate; will stale.","links":{"self":"/api/skills/migrate-ai-sdk-v6-to-v7","html":"/skills/migrate-ai-sdk-v6-to-v7","markdown":"/skills/migrate-ai-sdk-v6-to-v7.md"}},{"id":"add-webmcp","name":"Add WebMCP","tagline":"First-party WebMCP; not generic MCP builder","when":"Analyze an existing web application, identify safe user-visible capabilities across routes, forms, server actions, handlers, and schemas, then implement first-party WebMCP tools and validate discovery and invocation with Stagehand. Use when the user asks to make a codebase agent-ready, expose website features as WebMCP tools, or add WebMCP directly to an app rather than generating a standalone injection script from a URL.","license":"MIT (frontmatter; no LICENSE file)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/add-webmcp/SKILL.md","catch":"first-party WebMCP; not generic MCP builder. Loud: undeclared-repo LICENSE (frontmatter MIT; repo LICENSE 404).","links":{"self":"/api/skills/add-webmcp","html":"/skills/add-webmcp","markdown":"/skills/add-webmcp.md"}},{"id":"cookie-sync","name":"Cookie Sync","tagline":"Local Chrome cookies into Browserbase","when":"Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.","license":"MIT (frontmatter; no LICENSE file)","sourceUrl":"https://github.com/browserbase/skills/blob/main/skills/cookie-sync/SKILL.md","catch":"local Chrome cookies into Browserbase; never-fires without Browserbase. Loud LICENSE (frontmatter MIT; repo LICENSE 404).","links":{"self":"/api/skills/cookie-sync","html":"/skills/cookie-sync","markdown":"/skills/cookie-sync.md"}},{"id":"neon-postgres","name":"Neon Postgres","tagline":"Lakebase Postgres setup, pooled vs direct, DATABASE_URL","when":"Guides and best practices for Lakebase Postgres on Neon: setup, connection methods and drivers, pooled vs direct connections, DATABASE_URL, branching, schema migrations, autoscaling, scale-to-zero, instant restore, read replicas, connection pooling, IP allow lists, and logical replication. Also Lakebase Search (semantic, BM25, hybrid). Use when users ask about Lakebase Postgres, Neon setup, connect to Neon, Neon project, DATABASE_URL, serverless Postgres, Neon CLI, Neon MCP, Neon Auth, @neondatabase/serverless, @neondatabase/neon-js, scale to zero, Neon autoscaling, Neon read replica, Neon connection pooling, schema migrations, semantic search, vector search, full-text search, BM25, or hybrid search.","license":"Apache-2.0","sourceUrl":"https://github.com/neondatabase/agent-skills/blob/main/skills/neon-postgres/SKILL.md","catch":"Vendor lock: Neon/Lakebase setup, pooled vs direct, DATABASE_URL. Trigger steals Prisma/Supabase Postgres work. Free $0 at neon.tech/pricing (100 projects, 0.5 GB, 100 CU-hours; compute suspends at cap). Parent neon stays OUT (HOLD — always-on overview).","links":{"self":"/api/skills/neon-postgres","html":"/skills/neon-postgres","markdown":"/skills/neon-postgres.md"}},{"id":"neon-postgres-branches","name":"Neon Postgres Branches","tagline":"Pick/create Neon branch type; schema-only is Beta","when":"Choose and create the right Neon branch type for testing and development. Use when users ask about Neon branching, migration testing with real data, isolated test environments, schema-only branch workflows for sensitive data, resetting a branch from its parent, branch expiration and CI/CD branch lifecycles, or branch creation via Neon CLI or Neon MCP. Triggers include \"Neon branch\", \"test migrations safely\", \"branch production data\", \"schema-only branch\", \"reset branch\", \"branch per PR\", and \"sensitive data testing\". Not the neon-postgres setup skill.","license":"Apache-2.0","sourceUrl":"https://github.com/neondatabase/agent-skills/blob/main/skills/neon-postgres-branches/SKILL.md","catch":"Branch-type picker, not setup — distinct from neon-postgres. Schema-only branches are Beta. Free cap is 10 branches/project on neon.tech/pricing.","links":{"self":"/api/skills/neon-postgres-branches","html":"/skills/neon-postgres-branches","markdown":"/skills/neon-postgres-branches.md"}},{"id":"neon-functions","name":"Neon Functions","tagline":"Long-running Node HTTP on a Neon branch. Public beta","when":"Long-running, serverless Node.js HTTP functions deployed onto a Neon branch, with DATABASE_URL injected automatically and compute next to the data. Use when a user wants to host an API, an AI agent with long streaming responses, a WebSocket or SSE server, a webhook handler, a Discord bot, an MCP server, or any request/response workload that risks timing out on short lambda-style serverless — and wants it to branch with their database. Triggers include \"Neon Functions\", \"Neon Compute\", \"function that won't time out\", \"run code next to my database\", \"function logs\". Do not use for Browserbase Functions or generic AWS/Vercel lambda work that is not Neon.","license":"Apache-2.0","sourceUrl":"https://github.com/neondatabase/agent-skills/blob/main/skills/neon-functions/SKILL.md","catch":"Public beta. Vendor lock. False-fires on generic serverless — this is Neon Functions, not Vercel/AWS. NAME-COLLIDES with published Browserbase functions; slug is neon-functions, never functions. Free includes Functions capacity; costs past limits.","links":{"self":"/api/skills/neon-functions","html":"/skills/neon-functions","markdown":"/skills/neon-functions.md"}},{"id":"neon-object-storage","name":"Neon Object Storage","tagline":"S3-compatible storage that branches with Neon. Public beta","when":"S3-compatible object storage that branches with a Neon project so files and database rows stay in sync across dev, preview, and production. Use when the user wants buckets that fork with a Neon branch, uploads or attachments keyed from Postgres rows on the same branch, or S3 SDK/CLI access against Neon Object Storage. Not for static site hosting, AWS S3, Cloudflare R2, or UploadThing.","license":"Apache-2.0","sourceUrl":"https://github.com/neondatabase/agent-skills/blob/main/skills/neon-object-storage/SKILL.md","catch":"Public beta. Not AWS S3 and not R2 — Neon-only buckets that branch with Postgres. Vendor lock. Costs past the free Object Storage allowance.","links":{"self":"/api/skills/neon-object-storage","html":"/skills/neon-object-storage","markdown":"/skills/neon-object-storage.md"}},{"id":"livekit-agents","name":"LiveKit Agents","tagline":"Voice AI agent via LiveKit Cloud + Agents SDK","when":"Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to \"build a voice agent\", \"create a LiveKit agent\", \"add voice AI\", \"implement handoffs\", \"structure agent workflows\", or is working with LiveKit Agents SDK. Opinionated path is LiveKit Cloud + LiveKit Inference. Requires writing tests for all implementations. Skip when the job is self-hosting the LiveKit SFU or the deferred livekit-simulations skill.","license":"MIT","sourceUrl":"https://github.com/livekit/agent-skills/blob/main/skills/livekit-agents/SKILL.md","catch":"Cloud-only skill: skips self-host OSS. LiveKit Cloud + Inference is the path. Free Build $0, no CC, at livekit.com/pricing; Inference credits then paid. livekit-simulations stays DEFER.","links":{"self":"/api/skills/livekit-agents","html":"/skills/livekit-agents","markdown":"/skills/livekit-agents.md"}},{"id":"agent-owasp-compliance","name":"Agent OWASP Compliance","tagline":"OWASP ASI Top 10 audit before prod. Community Copilot skill","when":"Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use when evaluating an agent system's security posture before production deployment; running a compliance check against OWASP ASI 2026 standards; mapping existing security controls to the 10 agentic risks; generating a compliance report for security review or audit; comparing agent framework security features against the standard; or any request like \"is my agent OWASP compliant?\", \"check ASI compliance\", or \"agentic security audit\". Not for .mcp.json config audits (mcp-security-audit) and not Sentry security-review.","license":"MIT","sourceUrl":"https://github.com/github/awesome-copilot/blob/main/skills/agent-owasp-compliance/SKILL.md","catch":"Community Copilot skill, not OWASP-official. ASI Top 10 agent audit before prod — distinct from mcp-security-audit (.mcp.json) and from Sentry security-review.","links":{"self":"/api/skills/agent-owasp-compliance","html":"/skills/agent-owasp-compliance","markdown":"/skills/agent-owasp-compliance.md"}},{"id":"inngest-setup","name":"Inngest Setup","tagline":"Inngest Cloud + TypeScript setup. Hobby $0/mo, no CC","when":"Use when adding durable execution to a TypeScript project — retry-safe webhook handlers, background jobs that survive crashes, scheduled tasks, or long-running workflows that outlive a single request. Covers Inngest SDK installation, client config, environment variables, serve endpoints (Next.js, Express, Hono, Fastify), connect-as-worker mode, and the local dev server. TypeScript-focused; Python/Go belong in Inngest docs, not this skill.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-setup/SKILL.md","catch":"Assumes Inngest Cloud + TypeScript. Hobby is $0/mo, no CC, at inngest.com/pricing (50k executions, 5 concurrent steps, 500k events; pauses at quota).","links":{"self":"/api/skills/inngest-setup","html":"/skills/inngest-setup","markdown":"/skills/inngest-setup.md"}},{"id":"inngest-durable-functions","name":"Inngest Durable Functions","tagline":"Inngest steps, not BullMQ. Cloud + TypeScript","when":"Use when building functions that must survive process crashes, retry automatically on failure, run on a schedule, react to events, or maintain state across infrastructure failures — webhook handlers that drop events, flaky cron jobs, background jobs that fail mid-execution, or workflows that need to resume. Covers Inngest function configuration, triggers (events, cron, invoke), step execution and memoization, idempotency, cancellation, error handling, retries, logging, and observability. Not BullMQ, not Trigger.dev, not generic queues.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-durable-functions/SKILL.md","catch":"False-fires on BullMQ (and generic queues). This is Inngest durable functions — Cloud + TypeScript. Hobby pauses at quota.","links":{"self":"/api/skills/inngest-durable-functions","html":"/skills/inngest-durable-functions","markdown":"/skills/inngest-durable-functions.md"}},{"id":"inngest-events","name":"Inngest Events","tagline":"Inngest event schema; 24h dedupe is vendor-specific","when":"Use when designing event-driven workflows, decoupling services, implementing fan-out (one trigger, many downstream handlers), implementing idempotent event handling with IDs, or handling at-least-once delivery from external sources like Stripe webhooks. Covers Inngest event schema, payload format, naming conventions, IDs for idempotency, the ts param, fan-out patterns, and system events like inngest/function.failed.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-events/SKILL.md","catch":"24-hour event-ID dedupe is Inngest-specific — not Kafka, not SQS, not a generic idempotency key. Cloud + TypeScript.","links":{"self":"/api/skills/inngest-events","html":"/skills/inngest-events","markdown":"/skills/inngest-events.md"}},{"id":"inngest-flow-control","name":"Inngest Flow Control","tagline":"Concurrency/throttle/batch. Hobby is 5 concurrent steps","when":"Use when handling external API rate limits (OpenAI 429s, HubSpot or Stripe), preventing duplicate work from rapid event bursts (debouncing user actions), spreading load over time, ensuring per-tenant fairness, processing events in batches, limiting concurrent runs of the same operation, or assigning priority to important runs. Covers Inngest flow control: concurrency limits with keys, throttling, rate limiting, debounce, priority, singleton, and event batching.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-flow-control/SKILL.md","catch":"Loud: Hobby is 5 concurrent steps. This skill will prescribe concurrency, throttle, and batching the free plan cannot run. Upgrade or the controls lie.","links":{"self":"/api/skills/inngest-flow-control","html":"/skills/inngest-flow-control","markdown":"/skills/inngest-flow-control.md"}},{"id":"inngest-realtime","name":"Inngest Realtime","tagline":"v4-native inngest/realtime, not @inngest/realtime","when":"Use when streaming durable workflow updates to a UI in real time — live order status, AI agent token streaming from a function to the browser, log tailing for long-running jobs, or human-in-the-loop approval flows. Covers Inngest v4 native realtime: typed channels, publishing from inside step.run, minting subscription tokens via server actions, and consuming the stream from React/Next.js. Do not install the v3-era @inngest/realtime package on inngest@4.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-realtime/SKILL.md","catch":"v4-native: import from inngest/realtime. @inngest/realtime is the v3 package and will 401/TypeError on v4. Cloud + TypeScript.","links":{"self":"/api/skills/inngest-realtime","html":"/skills/inngest-realtime","markdown":"/skills/inngest-realtime.md"}},{"id":"inngest-agents","name":"Inngest Agents","tagline":"AgentKit lock. Durable agents on Inngest Cloud","when":"Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, crash-safe execution, and Agent Evals handoff. Covers AgentKit, step.ai, step.run, step.waitForEvent, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop. Skip generic LangGraph/CrewAI work that is not Inngest AgentKit.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-agents/SKILL.md","catch":"AgentKit lock: createAgent + step.ai on Inngest Cloud. Not a generic agent framework skill. Hobby 5-step cap still applies.","links":{"self":"/api/skills/inngest-agents","html":"/skills/inngest-agents","markdown":"/skills/inngest-agents.md"}},{"id":"inngest-v3-v4-migration","name":"Inngest v3 to v4 Migration","tagline":"SDK v3→v4. Stale the day v5 ships","when":"Use when upgrading an existing TypeScript codebase from Inngest SDK v3 to v4, or when fixing mixed v3/v4 API usage. Covers detecting current SDK usage, moving triggers into createFunction options, replacing EventSchemas with eventType/staticSchema, moving serve options to the client, updating realtime imports, rewriting step.invoke string IDs, checkpointing/serverless runtime settings, Connect option changes, and verification.","license":"Apache-2.0","sourceUrl":"https://github.com/inngest/inngest-skills/blob/main/skills/inngest-v3-v4-migration/SKILL.md","catch":"Version-gate: v3→v4 only. Stale the day v5 ships. Not a greenfield setup skill.","links":{"self":"/api/skills/inngest-v3-v4-migration","html":"/skills/inngest-v3-v4-migration","markdown":"/skills/inngest-v3-v4-migration.md"}},{"id":"convex-quickstart","name":"Convex Quickstart","tagline":"Next.js + Convex template. JSON-generated; can drift","when":"Get a barebones Convex + web template running from a one-sentence idea. Stand up a Next.js + Convex template locally with an anonymous dev deployment. Minimal: local dev servers, no publish step, no pre-baked auth. Use when starting a new Convex project or adding Convex to an existing app. Parent convex is HOLD — do not treat this as the always-on Convex overview.","license":"Apache-2.0","sourceUrl":"https://github.com/get-convex/agent-skills/blob/main/skills/convex-quickstart/SKILL.md","catch":"Next.js template path. SKILL.md is JSON-generated and can drift from live Convex APIs. Loud: convex.dev/pricing Free has hard caps; Starter is $0 base with a card. Parent convex stays HOLD.","links":{"self":"/api/skills/convex-quickstart","html":"/skills/convex-quickstart","markdown":"/skills/convex-quickstart.md"}},{"id":"convex-auth","name":"Convex Auth","tagline":"Convex Auth only — not Clerk or Better Auth","when":"Add authentication (passkeys/OAuth) to the current Convex app, including auth.config.ts wiring. Installs and wires @convex-dev/auth: provider, server config, client hooks, and a sign-in UI. Passkeys by default; password/OAuth only on explicit request. Not Clerk, not Better Auth, not Auth.js, not WorkOS.","license":"Apache-2.0","sourceUrl":"https://github.com/get-convex/agent-skills/blob/main/skills/convex-auth/SKILL.md","catch":"Convex Auth (@convex-dev/auth) only — not Clerk, not Better Auth. Missing auth.config.ts silently always-signed-out. Loud Free/Starter card on convex.dev/pricing.","links":{"self":"/api/skills/convex-auth","html":"/skills/convex-auth","markdown":"/skills/convex-auth.md"}},{"id":"convex-create-component","name":"Convex Create Component","tagline":"Convex Components with isolated tables, not React","when":"Build reusable Convex components with isolated tables and a small app-facing API. Use for new Convex components, reusable backend modules, integrations, or component boundary work. Not for one-off business logic, thin TypeScript utilities, React components, or app-level orchestration that should stay in convex/.","license":"Apache-2.0","sourceUrl":"https://github.com/get-convex/agent-skills/blob/main/skills/convex-create-component/SKILL.md","catch":"Convex Components — backend modules with isolated tables — not React components. Loud Free/Starter card.","links":{"self":"/api/skills/convex-create-component","html":"/skills/convex-create-component","markdown":"/skills/convex-create-component.md"}},{"id":"convex-migrate","name":"Convex Migrate","tagline":"Live-data backfill with @convex-dev/migrations, not Prisma","when":"Migrate schema and backfill data on a deployed Convex app using @convex-dev/migrations. Stage the schema change (new fields optional first), write a backfill that makes old rows valid, run it, verify, then tighten the validator. Use for live Convex data migrations. Not Prisma, not Drizzle, not neon-postgres-branches.","license":"Apache-2.0","sourceUrl":"https://github.com/get-convex/agent-skills/blob/main/skills/convex-migrate/SKILL.md","catch":"Live-data backfill on Convex, not Prisma. Tightening a validator before backfill rejects existing rows. Loud Free/Starter card.","links":{"self":"/api/skills/convex-migrate","html":"/skills/convex-migrate","markdown":"/skills/convex-migrate.md"}},{"id":"infisical-setup","name":"Infisical Setup","tagline":"CLI/SDK secrets into the app. Slug is infisical-setup","when":"Interactive setup for using Infisical as a secret management tool: local development (CLI), Docker (build-time and runtime injection), CI/CD (GitHub Actions, GitLab CI), Kubernetes (Operator + CRDs belong in infisical-kubernetes-operator), and application code (Node.js, Python, Go, Java, .NET, Ruby, PHP, Rust, C++ SDKs). Also machine identity auth methods. Use when someone asks about using Infisical, injecting secrets, infisical run, infisical init, Docker secrets, SDK initialization, or CI/CD secret injection. Not for pushing secrets out (infisical-secret-syncs) or self-hosting the platform (infisical-self-host).","license":"MIT","sourceUrl":"https://github.com/Infisical/ai-skills/blob/main/skills/infisical-setup/SKILL.md","catch":"Folder is infisical-setup; frontmatter name is infisical-user-setup-guide — catalog slug is infisical-setup. Cloud Free $0 forever (5 identities, unlimited projects, 3 envs, 10 secret syncs) at infisical.com/pricing. Not the k8s operator CRDs.","links":{"self":"/api/skills/infisical-setup","html":"/skills/infisical-setup","markdown":"/skills/infisical-setup.md"}},{"id":"infisical-kubernetes-operator","name":"Infisical Kubernetes Operator","tagline":"v1beta1 CRDs. v1alpha1 is a false-fire","when":"Use when installing or operating the Infisical Kubernetes Operator: Helm install, InfisicalSecret / InfisicalStaticSecret CRDs, auto-reload, and pushing secrets into cluster resources. Covers v1beta1 CRDs and legacy v1alpha1. Not generic External Secrets Operator, not infisical-setup SDK wiring, not infisical-self-host of the platform.","license":"MIT","sourceUrl":"https://github.com/Infisical/ai-skills/blob/main/skills/infisical-kubernetes-operator/SKILL.md","catch":"v1alpha1 is a false-fire — current CRDs are v1beta1. Dynamic-secret leases are paid Advanced even on self-host. Not the setup skill.","links":{"self":"/api/skills/infisical-kubernetes-operator","html":"/skills/infisical-kubernetes-operator","markdown":"/skills/infisical-kubernetes-operator.md"}},{"id":"infisical-self-host","name":"Infisical Self-Host","tagline":"MIT core only. ee/ needs LICENSE_KEY","when":"Deploy and operate Infisical self-hosted instances with Docker, Docker Compose, and Kubernetes. Covers architecture, environment variables, ENCRYPTION_KEY management, PostgreSQL, Redis (required noeviction), production hardening, FIPS, scaling, and HA. For deploying the Infisical platform itself. Not the Kubernetes Operator (separate Helm chart) and not using Infisical once running (infisical-setup).","license":"MIT","sourceUrl":"https://github.com/Infisical/ai-skills/blob/main/skills/infisical-self-host/SKILL.md","catch":"MIT core only. ee/ is not MIT — needs LICENSE_KEY. This deploys the platform; it does not inject secrets into an app.","links":{"self":"/api/skills/infisical-self-host","html":"/skills/infisical-self-host","markdown":"/skills/infisical-self-host.md"}},{"id":"infisical-secret-scanning","name":"Infisical Secret Scanning","tagline":"github-radar data source, not github. infisical scan","when":"Use when scanning repos and pipelines for leaked secrets with Infisical: GitHub/GitLab/Bitbucket data sources, infisical scan CLI, pre-commit hooks, and honey tokens. Not generic gitleaks-only work unless Infisical scanning is the product, and not infisical-setup secret injection.","license":"MIT","sourceUrl":"https://github.com/Infisical/ai-skills/blob/main/skills/infisical-secret-scanning/SKILL.md","catch":"GitHub data source is github-radar, not github. Distinct from setup and from syncs. Cloud Free $0 forever still caps identities and syncs.","links":{"self":"/api/skills/infisical-secret-scanning","html":"/skills/infisical-secret-scanning","markdown":"/skills/infisical-secret-scanning.md"}},{"id":"infisical-secret-syncs","name":"Infisical Secret Syncs","tagline":"Push secrets out. Free cap is 10 syncs","when":"Use when pushing Infisical secrets outward to third-party destinations (the 48 sync destinations, key schemas, initial-sync enums). This is secrets leaving Infisical. Not injecting secrets into an app (infisical-setup), not dynamic-secret leases, not secret scanning.","license":"MIT","sourceUrl":"https://github.com/Infisical/ai-skills/blob/main/skills/infisical-secret-syncs/SKILL.md","catch":"Push out, not pull in. Cloud Free cap is 10 secret syncs. Distinct from infisical-setup.","links":{"self":"/api/skills/infisical-secret-syncs","html":"/skills/infisical-secret-syncs","markdown":"/skills/infisical-secret-syncs.md"}},{"id":"react-email","name":"React Email","tagline":"Compose React email templates. Delivery still hits 100/day","when":"Use when building HTML email templates with React components, adding a visual email editor, rendering emails to HTML, or composing welcome emails, password resets, notifications, order confirmations, newsletters, and transactional templates. This is compose, not the HOLD parent resend send-API skill. Delivery through Resend still hits the Free 100/day and 3,000/mo caps.","license":"MIT","sourceUrl":"https://github.com/resend/resend-skills/blob/main/skills/react-email/SKILL.md","catch":"Compose templates. Sending still hits Resend Free $0/mo (3,000 emails/mo, 100/day, no overage). Overlaps HOLD parent resend on “sending”. Distinct from resend-cli.","links":{"self":"/api/skills/react-email","html":"/skills/react-email","markdown":"/skills/react-email.md"}},{"id":"resend-cli","name":"Resend CLI","tagline":"resend CLI for shell/CI. --react-email can steal compose","when":"Operate Resend from the terminal — send emails (including React Email .tsx via --react-email), manage domains, contacts, broadcasts, templates, webhooks, API keys, logs, automations, and events via the resend CLI. Use when the user wants Resend commands in the shell, scripts, or CI/CD. Always load before running resend commands. Parent resend and agent-email-inbox stay HOLD.","license":"MIT","sourceUrl":"https://github.com/resend/resend-skills/blob/main/skills/resend-cli/SKILL.md","catch":"Shell/CI. --react-email can steal react-email compose work. Free $0/mo still 3,000/mo and 100/day with no overage — the CLI will fail at the cap, not bill.","links":{"self":"/api/skills/resend-cli","html":"/skills/resend-cli","markdown":"/skills/resend-cli.md"}},{"id":"drizzle-migration-conflict","name":"Drizzle Migration Conflict","tagline":"Community v0.1. Not drizzle-team. Can steal generate","when":"Diagnose, repair, and prevent Drizzle Kit migration conflicts in team workflows: _journal.json, snapshot.json, non-commutative generated SQL, merge/rebase conflicts, drizzle-kit check. Prefer this when a Drizzle migration file conflicts after a pull, merge, rebase, or PR update. Official drizzle-team kit skills 404 on main. Not a clean-greenfield drizzle-kit generate unless a conflict already exists. hugo-to-markdown stays DEFER.","license":"Apache-2.0","sourceUrl":"https://github.com/chaunsin/agent-skills/blob/master/skills/drizzle-migration-conflict/SKILL.md","catch":"Community v0.1, not drizzle-team. Official kit skills 404 on main. Can steal a clean drizzle-kit generate.","links":{"self":"/api/skills/drizzle-migration-conflict","html":"/skills/drizzle-migration-conflict","markdown":"/skills/drizzle-migration-conflict.md"}},{"id":"elevenlabs-text-to-speech","name":"ElevenLabs Text-to-Speech","tagline":"Cloud TTS. Free 10k credits is minutes, not a product","when":"ElevenLabs cloud TTS. Needs API key. Not SFX, music, dubbing, Speech Engine, or LiveKit OSS.","license":"MIT","sourceUrl":"https://github.com/elevenlabs/skills/blob/main/text-to-speech/SKILL.md","catch":"Vendor lock. Needs API key. Free 10k credits/mo is minutes of audio, not a product. No commercial license on Free. Starter is 6 USD/mo not 5.","links":{"self":"/api/skills/elevenlabs-text-to-speech","html":"/skills/elevenlabs-text-to-speech","markdown":"/skills/elevenlabs-text-to-speech.md"}},{"id":"elevenlabs-speech-engine","name":"ElevenLabs Speech Engine","tagline":"Your runtime, their STT/TTS. Cloud + key. Not LiveKit OSS","when":"Real-time voice on a custom agent runtime via ElevenLabs Speech Engine (WebSocket, WebRTC, conversation tokens). They handle mic/STT/turn-taking/TTS; your server owns agent logic. Needs API key. Not LiveKit Agents OSS. Not the TTS-only skill.","license":"MIT","sourceUrl":"https://github.com/elevenlabs/skills/blob/main/speech-engine/SKILL.md","catch":"Your runtime, their STT/TTS. Cloud + API key, not LiveKit OSS. Free has no commercial license. Distinct from elevenlabs-text-to-speech.","links":{"self":"/api/skills/elevenlabs-speech-engine","html":"/skills/elevenlabs-speech-engine","markdown":"/skills/elevenlabs-speech-engine.md"}},{"id":"elevenlabs-sound-effects","name":"ElevenLabs Sound Effects","tagline":"Text-to-SFX, not speech. 200 credits/gen","when":"Generate sound effects from text with ElevenLabs: ambient, cinematic, UI, looping, duration. Not speech, not music, not dubbing. Needs API key. JS: scoped elevenlabs-js.","license":"MIT","sourceUrl":"https://github.com/elevenlabs/skills/blob/main/sound-effects/SKILL.md","catch":"Distinct from TTS. 200 credits/gen. Free 10k credits/mo; no commercial license on Free. Needs API key.","links":{"self":"/api/skills/elevenlabs-sound-effects","html":"/skills/elevenlabs-sound-effects","markdown":"/skills/elevenlabs-sound-effects.md"}},{"id":"elevenlabs-music","name":"ElevenLabs Music","tagline":"Music API. Commercial music is Starter+. 900 credits/min","when":"Generate music with the ElevenLabs Music API: instrumentals, lyrics, jingles, composition plans. Not TTS, SFX, or dubbing. Needs API key.","license":"MIT","sourceUrl":"https://github.com/elevenlabs/skills/blob/main/music/SKILL.md","catch":"Commercial music is Starter+ (6 USD/mo, not 5). 900 credits/min. Free has no commercial license. Distinct from TTS and sound-effects.","links":{"self":"/api/skills/elevenlabs-music","html":"/skills/elevenlabs-music","markdown":"/skills/elevenlabs-music.md"}},{"id":"elevenlabs-dubbing","name":"ElevenLabs Dubbing","tagline":"Dubbing Studio is Starter+. 2k-10k credits/min","when":"Dub audio or video into other languages with ElevenLabs Dubbing API v2, preserving original speakers. Use Dubbing Projects API, not legacy v1 create. Not TTS, SFX, or music. Needs API key.","license":"MIT","sourceUrl":"https://github.com/elevenlabs/skills/blob/main/dubbing/SKILL.md","catch":"Dubbing Studio is Starter+ (6 USD/mo). 2k-10k credits/min. Free has no commercial license. Distinct from TTS. Needs API key.","links":{"self":"/api/skills/elevenlabs-dubbing","html":"/skills/elevenlabs-dubbing","markdown":"/skills/elevenlabs-dubbing.md"}},{"id":"replicate-find-models","name":"Replicate Find Models","tagline":"Search Replicate models. Not Hugging Face Hub","when":"Find AI models on Replicate via search and curated collections. Always query the Replicate API for current models. Not Hugging Face Hub search. Not compare-models (cost/speed/quality pick) and not run-models.","license":"Apache-2.0","sourceUrl":"https://github.com/replicate/skills/blob/main/skills/find-models/SKILL.md","catch":"Vendor search on Replicate, not Hugging Face. No ongoing 0 USD hobby. PAYG at replicate.com/pricing. Try-for-Free is a one-time limited run, not a plan.","links":{"self":"/api/skills/replicate-find-models","html":"/skills/replicate-find-models","markdown":"/skills/replicate-find-models.md"}},{"id":"replicate-compare-models","name":"Replicate Compare Models","tagline":"Pick among Replicate models. Cost numbers stale","when":"Compare Replicate models by cost, speed, quality, and capabilities after a shortlist from find-models. Not discovery search. Cost and latency figures will go stale.","license":"Apache-2.0","sourceUrl":"https://github.com/replicate/skills/blob/main/skills/compare-models/SKILL.md","catch":"Pick vs find. Cost numbers will stale. No ongoing 0 USD hobby. PAYG. Try-for-Free is not a plan.","links":{"self":"/api/skills/replicate-compare-models","html":"/skills/replicate-compare-models","markdown":"/skills/replicate-compare-models.md"}},{"id":"replicate-run-models","name":"Replicate Run Models","tagline":"Paid predictions. Needs REPLICATE_API_TOKEN","when":"Run Replicate models via predictions, webhooks, streaming, files, concurrency. Needs REPLICATE_API_TOKEN. This is the paid API path. Try-for-Free UI is not this skill.","license":"Apache-2.0","sourceUrl":"https://github.com/replicate/skills/blob/main/skills/run-models/SKILL.md","catch":"Paid path. Needs REPLICATE_API_TOKEN. Try-for-Free is a one-time limited run, not this skill and not a plan. PAYG at replicate.com/pricing.","links":{"self":"/api/skills/replicate-run-models","html":"/skills/replicate-run-models","markdown":"/skills/replicate-run-models.md"}},{"id":"replicate-build-models","name":"Replicate Build Models","tagline":"Cog package. Skill still aims at Replicate deploy","when":"Package custom models with Cog (cog.yaml, predict.py, local serve/predict, GPU/Docker). Still aims at Replicate deploy. For pushing see publish-models.","license":"Apache-2.0","sourceUrl":"https://github.com/replicate/skills/blob/main/skills/build-models/SKILL.md","catch":"Cog is OSS; skill still aims at Replicate deploy. Local GPU/Docker. No 0 USD hobby. Try-for-Free is not a plan. Distinct from run and publish.","links":{"self":"/api/skills/replicate-build-models","html":"/skills/replicate-build-models","markdown":"/skills/replicate-build-models.md"}},{"id":"replicate-publish-models","name":"Replicate Publish Models","tagline":"cog push. Public model is not free inference","when":"Push custom models to Replicate with cog push or cog-safe-push and CI/CD. Not packaging (build-models) and not running others models (run-models).","license":"Apache-2.0","sourceUrl":"https://github.com/replicate/skills/blob/main/skills/publish-models/SKILL.md","catch":"cog push. Public model is not free inference. PAYG, no 0 USD hobby. Try-for-Free is a one-time limited run, not a plan.","links":{"self":"/api/skills/replicate-publish-models","html":"/skills/replicate-publish-models","markdown":"/skills/replicate-publish-models.md"}},{"id":"sanity-migration","name":"Sanity Migration","tagline":"Replatform to Sanity. Full CMS move, not PT conversion","when":"Plans CMS-to-Sanity replatforms from AEM, Contentful, Strapi, Webflow, WordPress, Payload, Drupal, Markdown/MDX. Full content strategy and ETL, not HTML/MD to Portable Text ingest alone, and not PT render.","license":"MIT","sourceUrl":"https://github.com/sanity-io/agent-toolkit/blob/main/skills/sanity-migration/SKILL.md","catch":"Vendor lock. Full CMS move, not PT conversion. Free 0 USD forever (20 seats, 2 permission roles, 2 datasets public only). Growth 15 USD/seat.","links":{"self":"/api/skills/sanity-migration","html":"/skills/sanity-migration","markdown":"/skills/sanity-migration.md"}},{"id":"sanity-portable-text-conversion","name":"Sanity Portable Text Conversion","tagline":"HTML/MD to Portable Text. Ingest, not replatform","when":"Convert HTML and Markdown into Portable Text for Sanity with @portabletext/markdown and @portabletext/block-tools. Ingest pipelines, not a full CMS replatform (sanity-migration) and not rendering PT out (serialization).","license":"MIT","sourceUrl":"https://github.com/sanity-io/agent-toolkit/blob/main/skills/portable-text-conversion/SKILL.md","catch":"Ingest, not replatform. Distinct from sanity-migration and from serialization (render). Free 0 USD forever still public-only datasets (2) and 2 roles. Growth 15 USD/seat.","links":{"self":"/api/skills/sanity-portable-text-conversion","html":"/skills/sanity-portable-text-conversion","markdown":"/skills/sanity-portable-text-conversion.md"}},{"id":"sanity-portable-text-serialization","name":"Sanity Portable Text Serialization","tagline":"PT to React/Svelte/Vue/HTML. Render, not ingest","when":"Render Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, plain text with @portabletext libraries. Custom serializers. Not converting HTML/MD into PT (conversion) and not CMS replatform (migration).","license":"MIT","sourceUrl":"https://github.com/sanity-io/agent-toolkit/blob/main/skills/portable-text-serialization/SKILL.md","catch":"Render, not ingest. Distinct from conversion and from sanity-migration. Free 0 USD forever: 20 seats, 2 roles, 2 public datasets. Growth 15 USD/seat.","links":{"self":"/api/skills/sanity-portable-text-serialization","html":"/skills/sanity-portable-text-serialization","markdown":"/skills/sanity-portable-text-serialization.md"}},{"id":"tanstack-ai-chat-experience","name":"TanStack AI Chat Experience","tagline":"False-fires on Vercel AI SDK streamText / useChat","when":"Build streaming chat with TanStack AI, not Vercel AI SDK streamText or useChat from ai. Sample path uses TanStack Start. Pinned library 0.42.0. OSS SDK is 0 USD; model calls need provider keys.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-core/chat-experience/SKILL.md","catch":"False-fires on Vercel AI SDK streamText / useChat from ai. Distinct from migrate-ai-sdk-v6-to-v7. Pinned 0.42.0. OSS SDK 0 USD; inference still needs provider keys.","links":{"self":"/api/skills/tanstack-ai-chat-experience","html":"/skills/tanstack-ai-chat-experience","markdown":"/skills/tanstack-ai-chat-experience.md"}},{"id":"tanstack-ai-tool-calling","name":"TanStack AI Tool Calling","tagline":"Isomorphic toolDefinition. Not OpenAI tools / Vercel tool()","when":"Type-safe isomorphic tools via TanStack AI toolDefinition that can run on server or client. Not OpenAI tools arrays and not Vercel AI SDK tool(). Pinned 0.42.0.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-core/tool-calling/SKILL.md","catch":"Isomorphic toolDefinition. False-fires on OpenAI tools and Vercel tool(). Distinct from chat-experience. OSS SDK 0 USD; provider keys still required.","links":{"self":"/api/skills/tanstack-ai-tool-calling","html":"/skills/tanstack-ai-tool-calling","markdown":"/skills/tanstack-ai-tool-calling.md"}},{"id":"tanstack-ai-media-generation","name":"TanStack AI Media Generation","tagline":"Not ElevenLabs/Replicate. generate* needs provider keys","when":"Generate image/audio/video via TanStack AI generate helpers and adapters. Not ElevenLabs skills and not Replicate run-models. Every generate call needs a paid provider key. Pinned 0.42.0.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-core/media-generation/SKILL.md","catch":"Not ElevenLabs or Replicate. Every generate-star needs a paid provider key. OSS SDK is 0 USD. Distinct from chat and tool-calling. Pinned 0.42.0.","links":{"self":"/api/skills/tanstack-ai-media-generation","html":"/skills/tanstack-ai-media-generation","markdown":"/skills/tanstack-ai-media-generation.md"}},{"id":"tanstack-ai-structured-outputs","name":"TanStack AI Structured Outputs","tagline":"Forbids provider-level json_schema you already set","when":"Structured outputs with TanStack AI via JSON Schema, Zod, ArkType, or Valibot. Do not also set provider-level json_schema when the SDK already owns the schema. Pinned 0.42.0. Not Vercel AI SDK generateObject.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-core/structured-outputs/SKILL.md","catch":"Forbids provider-level json_schema you already set on the SDK. Distinct from tool-calling. OSS 0 USD; provider keys still required. Pinned 0.42.0.","links":{"self":"/api/skills/tanstack-ai-structured-outputs","html":"/skills/tanstack-ai-structured-outputs","markdown":"/skills/tanstack-ai-structured-outputs.md"}},{"id":"tanstack-ai-adapter-configuration","name":"TanStack AI Adapter Configuration","tagline":"BytePlus TWO keys no fallback. Ollama is the 0 USD local path","when":"Configure TanStack AI provider adapters. BytePlus needs TWO keys with no fallback. Ollama is the only 0 USD local path. Other adapters need paid provider keys. Not chat UI. Pinned 0.42.0.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-core/adapter-configuration/SKILL.md","catch":"BytePlus TWO keys, no fallback. Ollama is the only 0 USD local path. Distinct from media-generation. Pinned 0.42.0.","links":{"self":"/api/skills/tanstack-ai-adapter-configuration","html":"/skills/tanstack-ai-adapter-configuration","markdown":"/skills/tanstack-ai-adapter-configuration.md"}},{"id":"tanstack-ai-ag-ui-protocol","name":"TanStack AI AG-UI Protocol","tagline":"Server AG-UI SSE/NDJSON. Not CopilotKit client","when":"Expose TanStack AI as a server AG-UI protocol over SSE or NDJSON. Not CopilotKit client widgets. Not chat-experience UI. Pinned 0.42.0.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-core/ag-ui-protocol/SKILL.md","catch":"Server AG-UI SSE/NDJSON, not CopilotKit client. Distinct from chat-experience. OSS SDK 0 USD; provider keys still required. Pinned 0.42.0.","links":{"self":"/api/skills/tanstack-ai-ag-ui-protocol","html":"/skills/tanstack-ai-ag-ui-protocol","markdown":"/skills/tanstack-ai-ag-ui-protocol.md"}},{"id":"tanstack-ai-code-mode","name":"TanStack AI Code Mode","tagline":"Isolate drivers. 0.3.8 vs ai-core 0.42.0. Not generic sandbox","when":"LLM-generated TypeScript in sandboxed isolate drivers via createCodeModeTool. Package @tanstack/ai-code-mode is 0.3.8, a different release train from ai-core 0.42.0. Not a generic sandbox skill. HOLD ai-core, middleware, custom-backend-integration.","license":"MIT","sourceUrl":"https://github.com/TanStack/ai/blob/main/skills/ai-code-mode/SKILL.md","catch":"Isolate drivers. 0.3.8 vs ai-core 0.42.0 different release train. Not a generic sandbox. Distinct from chat and tool-calling.","links":{"self":"/api/skills/tanstack-ai-code-mode","html":"/skills/tanstack-ai-code-mode","markdown":"/skills/tanstack-ai-code-mode.md"}},{"id":"tavily-search","name":"Tavily Search","tagline":"LLM-optimized search. Generic steal. 1 credit basic / 2 advanced","when":"Search the web with LLM-optimized results via the Tavily CLI (tvly). Use for search for / look up / find articles. Needs tvly login. Do not fall back to other search tools. Twin of firecrawl-build-search (that is Firecrawl /search in product code).","license":"MIT","sourceUrl":"https://github.com/tavily-ai/skills/blob/main/skills/tavily-search/SKILL.md","catch":"Loud generic steal (search for / look up). Body says do not fall back to other tools. Twins live firecrawl-build-search. 1 credit basic / 2 advanced. Researcher Free 0 USD/mo is 1,000 credits, no CC. PAYG 0.008 USD/credit. Needs tvly CLI + login.","links":{"self":"/api/skills/tavily-search","html":"/skills/tavily-search","markdown":"/skills/tavily-search.md"}},{"id":"tavily-research","name":"Tavily Research","tagline":"Cited multi-source report. Loud free-tier eater","when":"Cited multi-source research report via Tavily CLI. Not tavily-search fact-finding. Needs tvly login. Mini 4-110 credits, pro 15-250 vs Researcher Free 1,000/mo.","license":"MIT","sourceUrl":"https://github.com/tavily-ai/skills/blob/main/skills/tavily-research/SKILL.md","catch":"Loud free-tier eater: mini 4-110 credits, pro 15-250 vs 1,000/mo. One pro run can burn a quarter of Researcher. Distinct from tavily-search. PAYG 0.008 USD/credit after free.","links":{"self":"/api/skills/tavily-research","html":"/skills/tavily-research","markdown":"/skills/tavily-research.md"}},{"id":"pinecone-quickstart","name":"Pinecone Quickstart","tagline":"First-time Database vs Assistant tour. Not production schema","when":"First-time Pinecone tour: Database (integrated index, upsert, query via MCP + Python) or Assistant. Needs PINECONE_API_KEY and MCP. Not production schema design. Not upstash-vector-js.","license":"MIT","sourceUrl":"https://github.com/pinecone-io/skills/blob/main/skills/pinecone-quickstart/SKILL.md","catch":"First-time Database vs Assistant tour. PINECONE_API_KEY + MCP. Not production schema. Distinct from upstash-vector-js. Starter Free: 2 GB, 2M WU/mo, 1M RU/mo, AWS us-east-1 only. Builder 20 USD/mo. Standard 50 USD/mo min.","links":{"self":"/api/skills/pinecone-quickstart","html":"/skills/pinecone-quickstart","markdown":"/skills/pinecone-quickstart.md"}},{"id":"pinecone-query","name":"Pinecone Query","tagline":"Integrated indexes only. Standard/external must use pinecone-cli","when":"Query Pinecone integrated indexes (built-in embeddings) via MCP with natural language. Standard or external-embedding indexes must use pinecone-cli. MCP-only. Needs PINECONE_API_KEY. Not upstash-vector-js.","license":"MIT","sourceUrl":"https://github.com/pinecone-io/skills/blob/main/skills/pinecone-query/SKILL.md","catch":"LOUD: integrated indexes only (built-in embeddings). Standard/external must use pinecone-cli. MCP-only. Distinct from upstash-vector-js and from pinecone-quickstart.","links":{"self":"/api/skills/pinecone-query","html":"/skills/pinecone-query","markdown":"/skills/pinecone-query.md"}},{"id":"pinecone-cli","name":"Pinecone CLI","tagline":"pc CLI for all index types. False-fires on generic pc/redis-cli","when":"Use the Pinecone pc CLI for all index types (standard, integrated, sparse), batch ops, backups, namespaces, CI/CD. Unlike MCP which is integrated-indexes only. False-fires on generic pc or redis-cli already in PATH.","license":"MIT","sourceUrl":"https://github.com/pinecone-io/skills/blob/main/skills/pinecone-cli/SKILL.md","catch":"pc CLI for all index types. False-fires on generic pc/redis-cli in PATH. Distinct from pinecone-query (MCP integrated-only). Starter Free caps still apply.","links":{"self":"/api/skills/pinecone-cli","html":"/skills/pinecone-cli","markdown":"/skills/pinecone-cli.md"}},{"id":"pinecone-full-text-search","name":"Pinecone Full-Text Search","tagline":"SDK 10+ / API 2026-07. pinecone.preview deleted. Not Elasticsearch","when":"Pinecone full-text-search document index via graduated document-schema API. Python SDK >= 10.0.0, API 2026-07. pinecone.preview is deleted. Not Elasticsearch mapping. Distinct from pinecone-query vectors and from algolia search.","license":"MIT","sourceUrl":"https://github.com/pinecone-io/skills/blob/main/skills/pinecone-full-text-search/SKILL.md","catch":"SDK >=10 / API 2026-07. pinecone.preview deleted. Not Elasticsearch. Distinct from upstash-vector-js and from pinecone-query. Do not claim 5 indexes (unverified).","links":{"self":"/api/skills/pinecone-full-text-search","html":"/skills/pinecone-full-text-search","markdown":"/skills/pinecone-full-text-search.md"}},{"id":"pinecone-assistant","name":"Pinecone Assistant","tagline":"Managed RAG. Starter caps. Not LangChain RAG","when":"Create and chat with Pinecone Assistant, a managed RAG service with citations. Upload docs, ask questions. Not LangChain RAG pipelines and not pinecone-query vector search. Starter Assistant caps: 1GB / 500k in / 300k out / 1k ingest.","license":"MIT","sourceUrl":"https://github.com/pinecone-io/skills/blob/main/skills/pinecone-assistant/SKILL.md","catch":"Managed RAG. Starter Assistant caps 1GB / 500k in / 300k out / 1k ingest. Not LangChain RAG. Distinct from pinecone-quickstart Assistant tour and from upstash-vector-js.","links":{"self":"/api/skills/pinecone-assistant","html":"/skills/pinecone-assistant","markdown":"/skills/pinecone-assistant.md"}},{"id":"qdrant-deployment-options","name":"Qdrant Deployment Options","tagline":"Docker vs Cloud vs local vs Edge. Local Python in-memory is not server-format","when":"Choose Qdrant deployment: Docker, Cloud, local, or Edge. Local Python in-memory is NOT server-format compatible. Generic host steal. OSS self-host is 0 USD. Not Pinecone Cloud.","license":"Apache-2.0","sourceUrl":"https://github.com/qdrant/skills/blob/main/skills/qdrant-deployment-options/SKILL.md","catch":"Docker vs Cloud vs local vs Edge. Local Python in-memory is NOT server-format compatible. Generic host steal. Cloud Free unused clusters suspended after 1 week, deleted after 4 weeks. Distinct from pinecone-quickstart.","links":{"self":"/api/skills/qdrant-deployment-options","html":"/skills/qdrant-deployment-options","markdown":"/skills/qdrant-deployment-options.md"}},{"id":"qdrant-edge","name":"Qdrant Edge","tagline":"In-process shard. Beta API drifts. No one-call .sync(). Not sqlite-vec","when":"Build on Qdrant Edge, the embedded in-process shard (Python or Rust). Beta API drifts. No one-call .sync() to Cloud. Not sqlite-vec. Distinct from qdrant-deployment-options.","license":"Apache-2.0","sourceUrl":"https://github.com/qdrant/skills/blob/main/skills/qdrant-edge/SKILL.md","catch":"In-process shard. Beta API drifts. No one-call .sync(). Not sqlite-vec. Distinct from deployment-options. Cloud Free unused clusters still suspend after 1 week.","links":{"self":"/api/skills/qdrant-edge","html":"/skills/qdrant-edge","markdown":"/skills/qdrant-edge.md"}},{"id":"qdrant-model-migration","name":"Qdrant Model Migration","tagline":"Zero-downtime embedding switch. Named-vector add/delete needs v1.18+","when":"Zero-downtime embedding model switch in Qdrant. Named-vector add/delete needs v1.18+. v1.17 needs a new collection. Not a Pinecone namespace rewrite.","license":"Apache-2.0","sourceUrl":"https://github.com/qdrant/skills/blob/main/skills/qdrant-model-migration/SKILL.md","catch":"Zero-downtime embedding switch. Named-vector add/delete needs v1.18+; v1.17 needs a new collection. Not Pinecone namespace rewrite. Distinct from pinecone-query.","links":{"self":"/api/skills/qdrant-model-migration","html":"/skills/qdrant-model-migration","markdown":"/skills/qdrant-model-migration.md"}},{"id":"qdrant-multitenancy","name":"Qdrant Multitenancy","tagline":"Default payload-filter isolation, NOT collection-per-tenant","when":"Tenant isolation in Qdrant. Default is payload-filter isolation, NOT collection-per-tenant. Use when isolating customer data in one deployment.","license":"Apache-2.0","sourceUrl":"https://github.com/qdrant/skills/blob/main/skills/qdrant-multitenancy/SKILL.md","catch":"Default payload-filter isolation, NOT collection-per-tenant. Distinct from pinecone-cli namespaces and from model-migration. Cloud Free unused clusters suspend after 1 week.","links":{"self":"/api/skills/qdrant-multitenancy","html":"/skills/qdrant-multitenancy","markdown":"/skills/qdrant-multitenancy.md"}},{"id":"qdrant-version-upgrade","name":"Qdrant Version Upgrade","tagline":"Storage compat one minor only. Cloud automates; self-host stepwise","when":"Upgrade Qdrant server and SDKs. Storage compatibility is one minor only. Cloud automates skips; self-host must go stepwise. Zero-downtime needs replication >=2.","license":"Apache-2.0","sourceUrl":"https://github.com/qdrant/skills/blob/main/skills/qdrant-version-upgrade/SKILL.md","catch":"Storage compat one minor only. Cloud automates skips; self-host must do stepwise. Zero-downtime needs replication >=2. Distinct from model-migration.","links":{"self":"/api/skills/qdrant-version-upgrade","html":"/skills/qdrant-version-upgrade","markdown":"/skills/qdrant-version-upgrade.md"}},{"id":"qdrant-sizing","name":"Qdrant Sizing","tagline":"Cloud Free 1 GB will fail production assumptions. Not Pinecone RU/WU","when":"Size a Qdrant deployment (RAM, disk, CPU, nodes) before provisioning. Cloud Free is 1 GB RAM / 0.5 vCPU / 4 GB disk / 1 node and will fail production assumptions. Not a Pinecone RU/WU calculator.","license":"Apache-2.0","sourceUrl":"https://github.com/qdrant/skills/blob/main/skills/qdrant-sizing/SKILL.md","catch":"Cloud Free 1 GB will fail production assumptions. Not Pinecone RU/WU calculator. Unused free clusters suspended after 1 week, deleted after 4 weeks. Distinct from deployment-options.","links":{"self":"/api/skills/qdrant-sizing","html":"/skills/qdrant-sizing","markdown":"/skills/qdrant-sizing.md"}},{"id":"algolia-quickstart","name":"Algolia Quickstart","tagline":"Account/app from zero. Not index ops on existing app","when":"Set up Algolia from scratch: account, CLI login, provision an application, App ID and API key. Not index or data operations on an existing authenticated app. Vendor signup steal.","license":"MIT","sourceUrl":"https://github.com/algolia/skills/blob/main/skills/algolia-quickstart/SKILL.md","catch":"Account/app from zero. Not index ops on existing app. Vendor signup steal. Free plan: 50k records, 10k search req/mo, 5k recommend/mo, 10KB/record, 1GB/app, 1GB/index, max 1 application. Over Usage Limit may suspend OR inject Algolia attribution. Inactive >30 days may delete data.","links":{"self":"/api/skills/algolia-quickstart","html":"/skills/algolia-quickstart","markdown":"/skills/algolia-quickstart.md"}},{"id":"algolia-index-configuration","name":"Algolia Index Configuration","tagline":"Guidance-only. Live writes via cli/mcp. Not Elasticsearch mapping","when":"Algolia index settings and relevance guidance (searchableAttributes, facets, ranking, synonyms). Guidance-only; live writes go through algolia-cli or MCP. Not Elasticsearch mapping. Not pinecone-full-text-search.","license":"MIT","sourceUrl":"https://github.com/algolia/skills/blob/main/skills/algolia-index-configuration/SKILL.md","catch":"Guidance-only; live writes via cli/mcp. Not Elasticsearch mapping. Distinct from pinecone-full-text-search. Free over-limit may suspend or inject attribution.","links":{"self":"/api/skills/algolia-index-configuration","html":"/skills/algolia-index-configuration","markdown":"/skills/algolia-index-configuration.md"}},{"id":"algolia-instantsearch-ui","name":"Algolia InstantSearch UI","tagline":"JS/React/Vue. Angular InstantSearch deprecated. Not autocomplete","when":"Build Algolia InstantSearch results pages in JS/React/Vue. Angular InstantSearch is deprecated. Not autocomplete/typeahead (algolia-autocomplete). Not index configuration.","license":"MIT","sourceUrl":"https://github.com/algolia/skills/blob/main/skills/algolia-instantsearch-ui/SKILL.md","catch":"JS/React/Vue. Angular InstantSearch deprecated. Not autocomplete. Distinct from algolia-index-configuration. Free 10k search req/mo.","links":{"self":"/api/skills/algolia-instantsearch-ui","html":"/skills/algolia-instantsearch-ui","markdown":"/skills/algolia-instantsearch-ui.md"}},{"id":"algolia-autocomplete","name":"Algolia Autocomplete","tagline":"Typeahead not InstantSearch SRP. False-fires on any search box","when":"Algolia Autocomplete typeahead, query suggestions, federated panels. Not InstantSearch search-results pages. False-fires on any search box. Distinct from algolia-instantsearch-ui.","license":"MIT","sourceUrl":"https://github.com/algolia/skills/blob/main/skills/algolia-autocomplete/SKILL.md","catch":"Typeahead not InstantSearch SRP. False-fires on any search box. Distinct from instantsearch-ui. Free 10k search req/mo; over-limit may suspend or inject attribution.","links":{"self":"/api/skills/algolia-autocomplete","html":"/skills/algolia-autocomplete","markdown":"/skills/algolia-autocomplete.md"}},{"id":"algolia-crawler","name":"Algolia Crawler","tagline":"Crawl into Algolia index, not markdown dump. Over-limit = suspend or attribution","when":"Crawl pages into an Algolia index via the Algolia CLI. Not a markdown dump. Not Firecrawl extract. Do not claim 5k crawls/mo (not on the Free plan policy page).","license":"MIT","sourceUrl":"https://github.com/algolia/skills/blob/main/skills/algolia-crawler/SKILL.md","catch":"Crawl into Algolia index, not markdown dump. Free over-limit may suspend OR inject Algolia attribution. Inactive >30 days may delete data. Do not claim 5k crawls/mo.","links":{"self":"/api/skills/algolia-crawler","html":"/skills/algolia-crawler","markdown":"/skills/algolia-crawler.md"}},{"id":"algolia-migration","name":"Algolia Migration","tagline":"SDK major v3 to v4 / v4 to v5. Dart excluded. Not data/index migration","when":"Migrate Algolia API client code across major SDK versions (v3 to v4, v4 to v5). Dart is excluded. Not data or index migration. Distinct from sanity-migration and from algolia-quickstart.","license":"MIT","sourceUrl":"https://github.com/algolia/skills/blob/main/skills/algolia-migration/SKILL.md","catch":"SDK major v3 to v4 / v4 to v5. Dart excluded. Not data/index migration. Distinct from pinecone-full-text-search and from sanity-migration.","links":{"self":"/api/skills/algolia-migration","html":"/skills/algolia-migration","markdown":"/skills/algolia-migration.md"}},{"id":"duckdb-install-duckdb","name":"DuckDB Install Extension","tagline":"INSTALL extension, not brew-installing DuckDB","when":"Install or update DuckDB extensions (INSTALL / name@repo). Not first-time CLI or brew install of DuckDB itself. False-fires on first-time CLI setup. Local OSS 0 USD, no cloud, no key.","license":"MIT","sourceUrl":"https://github.com/duckdb/duckdb-skills/blob/main/skills/install-duckdb/SKILL.md","catch":"INSTALL extension NOT brew-installing DuckDB. False-fires on first-time CLI setup. Local OSS 0 USD, no cloud, no key. Distinct from Neon/PlanetScale SQL.","links":{"self":"/api/skills/duckdb-install-duckdb","html":"/skills/duckdb-install-duckdb","markdown":"/skills/duckdb-install-duckdb.md"}},{"id":"duckdb-read-file","name":"DuckDB Read File","tagline":"whats in this file steal vs Read tool. Not for source code","when":"Read data files (CSV, JSON, Parquet, Avro, Excel, spatial, SQLite) or remote URLs with DuckDB. Steals whats in this file vs the Read tool. Not for source code. Distinct from duckdb-convert-file.","license":"MIT","sourceUrl":"https://github.com/duckdb/duckdb-skills/blob/main/skills/read-file/SKILL.md","catch":"whats in this file steal vs Read tool. Not for source code. Local OSS 0 USD, no cloud, no key. Distinct from Neon SQL and from convert-file.","links":{"self":"/api/skills/duckdb-read-file","html":"/skills/duckdb-read-file","markdown":"/skills/duckdb-read-file.md"}},{"id":"duckdb-convert-file","name":"DuckDB Convert File","tagline":"Generic convert steal (pandoc/ffmpeg). Data files only","when":"Convert data files with DuckDB (CSV, Parquet, JSON, Excel, GeoJSON). Generic convert steal vs pandoc/ffmpeg. Data files only, not documents or video.","license":"MIT","sourceUrl":"https://github.com/duckdb/duckdb-skills/blob/main/skills/convert-file/SKILL.md","catch":"Generic convert steal (pandoc/ffmpeg). Data files only. Distinct from duckdb-read-file. Local OSS 0 USD, no key.","links":{"self":"/api/skills/duckdb-convert-file","html":"/skills/duckdb-convert-file","markdown":"/skills/duckdb-convert-file.md"}},{"id":"duckdb-attach-db","name":"DuckDB Attach DB","tagline":"Session-state is Claude-skill local, not DuckDB server attach","when":"Attach a DuckDB database file and write a SQL state file so later queries restore the session. Session-state convention is Claude-skill local, not DuckDB server ATTACH.","license":"MIT","sourceUrl":"https://github.com/duckdb/duckdb-skills/blob/main/skills/attach-db/SKILL.md","catch":"Session-state convention is Claude-skill local, not DuckDB server attach. Distinct from read-file. Local OSS 0 USD, no cloud, no key. Distinct from Neon/PlanetScale.","links":{"self":"/api/skills/duckdb-attach-db","html":"/skills/duckdb-attach-db","markdown":"/skills/duckdb-attach-db.md"}},{"id":"duckdb-s3-explore","name":"DuckDB S3 Explore","tagline":"Query s3:// r2:// gs:// without download. Needs provider creds. Not AWS CLI ls","when":"Explore and query s3:// r2:// gs:// without downloading. Needs provider creds. Not AWS CLI ls. DuckDB itself is local OSS 0 USD.","license":"MIT","sourceUrl":"https://github.com/duckdb/duckdb-skills/blob/main/skills/s3-explore/SKILL.md","catch":"Query s3:// r2:// gs:// without download. Needs provider creds. Not AWS CLI ls. Distinct from read-file local paths. DuckDB is 0 USD local; object-store bills separately.","links":{"self":"/api/skills/duckdb-s3-explore","html":"/skills/duckdb-s3-explore","markdown":"/skills/duckdb-s3-explore.md"}},{"id":"duckdb-spatial","name":"DuckDB Spatial","tagline":"Geo steal. Spatial extension must already be installed","when":"Spatial questions in DuckDB: locations, distances, GeoJSON, Shapefile, GeoParquet. Geo steal. Spatial extension must already be installed (use duckdb-install-duckdb first). HOLD query, duckdb-docs, read-memories.","license":"MIT","sourceUrl":"https://github.com/duckdb/duckdb-skills/blob/main/skills/spatial/SKILL.md","catch":"Geo steal. Spatial extension must already be installed. Distinct from install-duckdb and from s3-explore. Local OSS 0 USD, no key.","links":{"self":"/api/skills/duckdb-spatial","html":"/skills/duckdb-spatial","markdown":"/skills/duckdb-spatial.md"}},{"id":"knock-setup","name":"Knock Setup","tagline":"Vendor onboarding. Always asks for Knock account first","when":"End-to-end Knock setup: connect tooling, design notification workflows, wire triggers. Always asks for a Knock account first. Not generic notifications and not Resend send-API.","license":"MIT","sourceUrl":"https://github.com/knocklabs/skills/blob/main/skills/knock-setup/SKILL.md","catch":"Vendor onboarding. Always asks for Knock account first. Not generic notifications. Distinct from resend-cli. Developer 0 USD/mo: 10k messages, 500 guide AU. A message = one user times one channel. Downstream SendGrid/Twilio still billed.","links":{"self":"/api/skills/knock-setup","html":"/skills/knock-setup","markdown":"/skills/knock-setup.md"}},{"id":"knock-in-app-ui","name":"Knock In-App UI","tagline":"React-only. Developer cap 500 guide AU. Branding on feeds is Starter-gated","when":"Knock in-app UI in React: feeds and guides. React-only. Developer cap 500 guide active users. Knock branding on feeds is Starter-gated (250 USD/mo). Not knock-setup onboarding.","license":"MIT","sourceUrl":"https://github.com/knocklabs/skills/blob/main/skills/knock-in-app-ui/SKILL.md","catch":"React-only. Developer cap 500 guide AU. Branding on feeds is Starter-gated (250 USD/mo). Distinct from knock-setup and from react-email.","links":{"self":"/api/skills/knock-in-app-ui","html":"/skills/knock-in-app-ui","markdown":"/skills/knock-in-app-ui.md"}},{"id":"knock-cli","name":"Knock CLI","tagline":"Pull/push workflows via CLI. Not MCP path","when":"Knock CLI to pull/push workflows, templates, and notification resources. Not the MCP path. Distinct from knock-setup and from resend-cli.","license":"MIT","sourceUrl":"https://github.com/knocklabs/skills/blob/main/skills/knock-cli/SKILL.md","catch":"Pull/push workflows via CLI. Not MCP path. Distinct from resend-cli. Developer 10k messages/mo; a message = one user times one channel. Downstream SendGrid/Twilio still billed.","links":{"self":"/api/skills/knock-cli","html":"/skills/knock-cli","markdown":"/skills/knock-cli.md"}},{"id":"knock-migrate-to-knock","name":"Knock Migrate to Knock","tagline":"Discovery-only. Writes knock-plan.md. Vendor steal vs Resend/SendGrid","when":"Discover existing messaging (Braze, Courier, Customer.io, Iterable, SendGrid, custom) and map it to Knock. Discovery-only: will not mutate Knock resources. Writes knock-plan.md. Vendor steal vs Resend/SendGrid. HOLD lifecycle-opportunities, notification-best-practices, product-messaging-strategy.","license":"MIT","sourceUrl":"https://github.com/knocklabs/skills/blob/main/skills/knock-migrate-to-knock/SKILL.md","catch":"Discovery-only will not mutate but vendor steal vs Resend/SendGrid. Writes knock-plan.md. Distinct from knock-setup and from resend-cli. No Grafana dump.","links":{"self":"/api/skills/knock-migrate-to-knock","html":"/skills/knock-migrate-to-knock","markdown":"/skills/knock-migrate-to-knock.md"}},{"id":"chdb-datastore","name":"chDB DataStore","tagline":"Pandas API on in-process ClickHouse. Not a server. Distinct from chdb-sql","when":"Use chDB DataStore as a pandas-compatible API backed by in-process ClickHouse. Change import pandas as pd to import chdb.datastore as pd. Not raw SQL (chdb-sql) and not a ClickHouse server. Python 3.9+, pip install chdb.","license":"Apache-2.0","sourceUrl":"https://github.com/ClickHouse/agent-skills/blob/main/skills/chdb-datastore/SKILL.md","catch":"In-process pandas twin, not a ClickHouse server. OSS/chDB is 0 USD. ClickHouse Cloud is a trial plus 300 USD credits, not a hobby plan. Do not invent a 30-day window. Distinct from chdb-sql.","links":{"self":"/api/skills/chdb-datastore","html":"/skills/chdb-datastore","markdown":"/skills/chdb-datastore.md"}},{"id":"chdb-sql","name":"chDB SQL","tagline":"In-process ClickHouse SQL. Not DataStore pandas. No server","when":"Run ClickHouse SQL in-process via chdb.query() / Session on local files, S3, Postgres, MySQL, Iceberg, Delta with no server. Not pandas DataStore chaining (chdb-datastore) and not ClickHouse server admin (infra-clickhouse).","license":"Apache-2.0","sourceUrl":"https://github.com/ClickHouse/agent-skills/blob/main/skills/chdb-sql/SKILL.md","catch":"Embedded SQL, not pandas DataStore. OSS/chDB 0 USD. Cloud is trial plus 300 USD credits, not hobby. Distinct from chdb-datastore and from infra-clickhouse. HOLD troubleshooting/best-practices/architecture-advisor.","links":{"self":"/api/skills/chdb-sql","html":"/skills/chdb-sql","markdown":"/skills/chdb-sql.md"}},{"id":"clickhouse-js-node-coding","name":"ClickHouse JS Node Coding","tagline":"@clickhouse/client Node only. Not client-web / Edge / Workers","when":"Write idiomatic Node.js code with @clickhouse/client (Next Node runtime, RSC, Server Actions). Never @clickhouse/client-web. Not browser, Edge, or Cloudflare Workers. Not RowBinary codecs (clickhouse-js-node-rowbinary). HOLD clickhouse-js-node-troubleshooting.","license":"Apache-2.0","sourceUrl":"https://github.com/ClickHouse/agent-skills/blob/main/skills/clickhouse-js-node-coding/SKILL.md","catch":"Node-only @clickhouse/client. False-fires on Edge/Workers/client-web. Distinct from rowbinary and from chdb-sql. Cloud is trial plus 300 USD credits, not a hobby plan.","links":{"self":"/api/skills/clickhouse-js-node-coding","html":"/skills/clickhouse-js-node-coding","markdown":"/skills/clickhouse-js-node-coding.md"}},{"id":"clickhouse-js-node-rowbinary","name":"ClickHouse JS Node RowBinary","tagline":"RowBinary codec generator. Not JSONEachRow. Node only","when":"Generate TypeScript readers/writers for ClickHouse RowBinary / RowBinaryWithNames / RowBinaryWithNamesAndTypes on Node. Prefer JSONEachRow for string-heavy results (clickhouse-js-node-coding). Not browser. HOLD troubleshooting.","license":"Apache-2.0","sourceUrl":"https://github.com/ClickHouse/agent-skills/blob/main/skills/clickhouse-js-node-rowbinary/SKILL.md","catch":"RowBinary codecs, not JSONEachRow. Node only. Distinct from clickhouse-js-node-coding. Cloud is trial plus 300 USD credits, not hobby. Do not invent a 30-day window.","links":{"self":"/api/skills/clickhouse-js-node-rowbinary","html":"/skills/clickhouse-js-node-rowbinary","markdown":"/skills/clickhouse-js-node-rowbinary.md"}},{"id":"infra-clickhouse","name":"Infra ClickHouse","tagline":"clickhousectl local vs Cloud. Cloud is trial plus credits, not hobby","when":"Set up ClickHouse with clickhousectl: local server for development, or managed ClickHouse Cloud for production. Default to local; ask before creating Cloud. Not chDB in-process and not JS client coding. HOLD architecture-advisor, best-practices, troubleshooting.","license":"Apache-2.0","sourceUrl":"https://github.com/ClickHouse/agent-skills/blob/main/skills/infra-clickhouse/SKILL.md","catch":"clickhousectl. Local OSS 0 USD. Cloud is a trial plus 300 USD credits, NOT a hobby plan. Do not invent a 30-day window. Distinct from chdb-sql and from clickhouse-js-node-coding.","links":{"self":"/api/skills/infra-clickhouse","html":"/skills/infra-clickhouse","markdown":"/skills/infra-clickhouse.md"}},{"id":"motherduck-connect","name":"MotherDuck Connect","tagline":"Postgres endpoint false-fires as Neon/PlanetScale. Not local DuckDB","when":"Connect an app to MotherDuck. Recommended path is the Postgres-compatible endpoint, which false-fires as Neon or PlanetScale. Native DuckDB API is not the default. Not local DuckDB (duckdb-*). Lite 0 USD/mo: 10 GB, 10 CU hours Pulse, 3 users / 2 service accounts.","license":"MIT","sourceUrl":"https://github.com/motherduckdb/agent-skills/blob/main/skills/motherduck-connect/SKILL.md","catch":"Postgres endpoint false-fires as Neon/PlanetScale. Recommended path is not local DuckDB. Distinct from duckdb-attach-db. Lite 0 USD/mo: 10 GB storage, 10 CU hours Pulse, 3 users / 2 service accounts. Pulse only on Lite.","links":{"self":"/api/skills/motherduck-connect","html":"/skills/motherduck-connect","markdown":"/skills/motherduck-connect.md"}},{"id":"motherduck-cli","name":"MotherDuck CLI","tagline":"Not MCP. Dives/Flights are MotherDuck-specific. Lite Flights 30 min/day","when":"Operate MotherDuck from a terminal: auth, query, Dive/Flight authoring. Not MCP (chat-only exploration). Dives and Flights are MotherDuck-specific. Lite Flights 30 min/day without CC. Distinct from duckdb-install-duckdb.","license":"MIT","sourceUrl":"https://github.com/motherduckdb/agent-skills/blob/main/skills/motherduck-cli/SKILL.md","catch":"Not MCP. Dives/Flights are MotherDuck-specific. Lite Flights 30 min/day without CC. Distinct from duckdb-* CLI. Lite 0 USD/mo still 10 GB / 10 CU hours Pulse / 2 service accounts.","links":{"self":"/api/skills/motherduck-cli","html":"/skills/motherduck-cli","markdown":"/skills/motherduck-cli.md"}},{"id":"motherduck-load-data","name":"MotherDuck Load Data","tagline":"DuckDB convert/read-file twin but destination is MotherDuck. 10 GB Lite cap","when":"Load data into MotherDuck from files, object storage, HTTPS, dataframes, or external DBs. Twin of duckdb-convert-file / duckdb-read-file but destination is MotherDuck. Hits the Lite 10 GB cap. Not duckdb-s3-explore local.","license":"MIT","sourceUrl":"https://github.com/motherduckdb/agent-skills/blob/main/skills/motherduck-load-data/SKILL.md","catch":"DuckDB convert/read-file twin but destination MotherDuck. Lite 10 GB storage cap. Distinct from duckdb-convert-file and from duckdb-s3-explore. Pulse CU hours still apply.","links":{"self":"/api/skills/motherduck-load-data","html":"/skills/motherduck-load-data","markdown":"/skills/motherduck-load-data.md"}},{"id":"motherduck-share-data","name":"MotherDuck Share Data","tagline":"Zero-copy metadata clones. Not S3 sharing. Not DuckDB ATTACH of a file","when":"Create MotherDuck data shares: zero-copy, read-only metadata clones of a database. Not S3 sharing and not DuckDB ATTACH of a file (duckdb-attach-db). Recipients ATTACH the share read-only.","license":"MIT","sourceUrl":"https://github.com/motherduckdb/agent-skills/blob/main/skills/motherduck-share-data/SKILL.md","catch":"Zero-copy metadata clones, not S3 sharing, not DuckDB ATTACH of a file. Distinct from duckdb-attach-db and from motherduck-load-data. Lite still 3 users / 2 service accounts.","links":{"self":"/api/skills/motherduck-share-data","html":"/skills/motherduck-share-data","markdown":"/skills/motherduck-share-data.md"}},{"id":"motherduck-ducklake","name":"MotherDuck DuckLake","tagline":"Default is native storage. Over-fires on lakehouse / Iceberg-on-S3","when":"Decide when DuckLake is the right MotherDuck storage vs native MotherDuck (the default). Over-fires on lakehouse / Iceberg-on-S3. Native storage is often faster for reads. Not motherduck-load-data ingestion.","license":"MIT","sourceUrl":"https://github.com/motherduckdb/agent-skills/blob/main/skills/motherduck-ducklake/SKILL.md","catch":"Default native storage; over-fires on lakehouse / fights Iceberg-on-S3. Distinct from duckdb-spatial and from motherduck-load-data. Lite 10 GB still applies to native storage.","links":{"self":"/api/skills/motherduck-ducklake","html":"/skills/motherduck-ducklake","markdown":"/skills/motherduck-ducklake.md"}},{"id":"motherduck-rest-api","name":"MotherDuck REST API","tagline":"Control plane, not SQL. Lite service-account cap is 2","when":"MotherDuck REST control-plane admin (tokens, orgs, service accounts). Not SQL. Uses MOTHERDUCK_ADMIN_TOKEN, never for database connections (motherduck-connect). Lite service-account cap is 2. HOLD query, duckdb-sql, explore, migrate-to-motherduck, pricing-roi, partner-delivery, build-*.","license":"MIT","sourceUrl":"https://github.com/motherduckdb/agent-skills/blob/main/skills/motherduck-rest-api/SKILL.md","catch":"Control plane not SQL. Lite service-account cap is 2. Distinct from motherduck-connect and from duckdb-*. No 21-file dump.","links":{"self":"/api/skills/motherduck-rest-api","html":"/skills/motherduck-rest-api","markdown":"/skills/motherduck-rest-api.md"}},{"id":"huggingface-spaces","name":"Hugging Face Spaces","tagline":"Host Gradio/Docker/Static. Free: Static + max 2 ZeroGPU. cpu-basic not free","when":"Host apps on Hugging Face Spaces (Gradio, Docker, or Static). Overlaps huggingface-gradio for UI — this is hosting. Free account: Static plus max 2 ZeroGPU only. cpu-basic is NOT a free fallback. Distinct from huggingface-lora-space-builder (publishes a LoRA demo). Do NOT dump hf-cloud-sagemaker.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-spaces/SKILL.md","catch":"Hosting, not Gradio UI. Free: Static + max 2 ZeroGPU only; cpu-basic is NOT a free fallback. Distinct from huggingface-gradio. Gradio/Docker need PRO except the two ZeroGPU slots.","links":{"self":"/api/skills/huggingface-spaces","html":"/skills/huggingface-spaces","markdown":"/skills/huggingface-spaces.md"}},{"id":"huggingface-zerogpu","name":"Hugging Face ZeroGPU","tagline":"@spaces.GPU / pickle isolation. Gradio ZeroGPU only — Docker/Static will not schedule","when":"Write or review @spaces.GPU ZeroGPU code: pickle isolation, duration/quota, no torch.compile. Gradio ZeroGPU only — Docker, Static, and Streamlit-as-Docker will not schedule. Distinct from huggingface-spaces hosting and from huggingface-gradio UI.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-zerogpu/SKILL.md","catch":"@spaces.GPU / pickle isolation. Gradio ZeroGPU only — Docker/Static/Streamlit-as-Docker will not schedule. Distinct from huggingface-spaces. Free still max 2 ZeroGPU Spaces.","links":{"self":"/api/skills/huggingface-zerogpu","html":"/skills/huggingface-zerogpu","markdown":"/skills/huggingface-zerogpu.md"}},{"id":"huggingface-lora-space-builder","name":"Hugging Face LoRA Space Builder","tagline":"Publishes a real private Space for a Hub LoRA. Steals make a Space/demo","when":"Build and publish a Gradio Space for a user-provided Hub LoRA (private by default, ZeroGPU). Steals make a Space/demo vs huggingface-spaces. Output is a published Space, not a local script. Distinct from huggingface-zerogpu coding rules.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/huggingface-lora-space-builder/SKILL.md","catch":"Publishes a real private Space for a Hub LoRA. make a Space/demo steal vs huggingface-spaces. Distinct from huggingface-zerogpu. Free ZeroGPU cap still 2 Spaces.","links":{"self":"/api/skills/huggingface-lora-space-builder","html":"/skills/huggingface-lora-space-builder","markdown":"/skills/huggingface-lora-space-builder.md"}},{"id":"huggingface-train-sentence-transformers","name":"Hugging Face Train Sentence Transformers","tagline":"Router not a manual. Skip references/ and trainers break. Not generic embedding","when":"Train or fine-tune sentence-transformers (SentenceTransformer, CrossEncoder, SparseEncoder, MultiVectorEncoder). This SKILL.md is a router — skip references/ and trainers break. Not a generic embedding skill. Distinct from huggingface-trl-training.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/train-sentence-transformers/SKILL.md","catch":"Router-not-manual; skip references/ and trainers break. Not generic embedding. Distinct from huggingface-trl-training and from huggingface-vision-trainer. GPU assumed, not a 0 USD laptop.","links":{"self":"/api/skills/huggingface-train-sentence-transformers","html":"/skills/huggingface-train-sentence-transformers","markdown":"/skills/huggingface-train-sentence-transformers.md"}},{"id":"huggingface-trl-training","name":"Hugging Face TRL Training","tagline":"TRL CLI SFT/DPO/GRPO. Not huggingface-llm-trainer. GPU assumed, not 0 USD laptop","when":"Train with TRL CLI (trl sft / dpo / grpo / kto / rloo / reward). Not huggingface-llm-trainer. GPU assumed, not a 0 USD laptop. Distinct from huggingface-train-sentence-transformers and from huggingface-vision-trainer.","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/trl-training/SKILL.md","catch":"TRL CLI SFT/DPO/GRPO. Not huggingface-llm-trainer. GPU assumed; not a 0 USD laptop. Distinct from train-sentence-transformers. Cloud GPU costs apply.","links":{"self":"/api/skills/huggingface-trl-training","html":"/skills/huggingface-trl-training","markdown":"/skills/huggingface-trl-training.md"}},{"id":"huggingface-hf-mem","name":"Hugging Face hf-mem","tagline":"VRAM estimate via HTTP Range, no download. Needs uvx. Gated models need HF_TOKEN","when":"Estimate VRAM/memory to load Safetensors or GGUF from the Hub via HTTP Range — no weight download. Needs uvx. Gated/private models need HF_TOKEN. Distinct from huggingface-local-models (actually running GGUF).","license":"Apache-2.0","sourceUrl":"https://github.com/huggingface/skills/blob/main/skills/hf-mem/SKILL.md","catch":"VRAM estimate via HTTP Range, no download. Needs uvx. Gated models need HF_TOKEN. Distinct from huggingface-local-models. Does not train or host.","links":{"self":"/api/skills/huggingface-hf-mem","html":"/skills/huggingface-hf-mem","markdown":"/skills/huggingface-hf-mem.md"}},{"id":"novu-trigger-notification","name":"Novu Trigger Notification","tagline":"knock-setup twin. Topic fan-out bills one run per matching subscriber","when":"Trigger Novu workflows (single, bulk, broadcast, topic). knock-setup twin for sending. Topic fan-out bills one workflow run per matching subscriber vs Free 10,000 runs/mo. Meter is workflow runs, not Knock messages. Downstream email/SMS still billed. Distinct from knock-setup.","license":"MIT","sourceUrl":"https://github.com/novuhq/skills/blob/main/skills/trigger-notification/SKILL.md","catch":"knock-setup twin. Topic fan-out bills one run per matching subscriber vs 10k Free runs/mo. Meter is workflow runs, NOT Knock messages. Over-limit does not throttle. Distinct from knock-setup. Downstream SendGrid/Twilio still billed.","links":{"self":"/api/skills/novu-trigger-notification","html":"/skills/novu-trigger-notification","markdown":"/skills/novu-trigger-notification.md"}},{"id":"novu-manage-subscribers","name":"Novu Manage Subscribers","tagline":"Not user-auth. subscriberId is not a Clerk/Auth.js user","when":"Create, update, search, delete Novu subscribers and topics. Not user-auth — subscriberId is not a Clerk or Auth.js user. Distinct from novu-trigger-notification and from knock-setup identify.","license":"MIT","sourceUrl":"https://github.com/novuhq/skills/blob/main/skills/manage-subscribers/SKILL.md","catch":"Not user-auth; subscriberId ≠ Clerk/Auth.js user. Distinct from knock-setup and from novu-trigger-notification. Cloud Free 10k workflow runs/mo still applies when you later trigger.","links":{"self":"/api/skills/novu-manage-subscribers","html":"/skills/novu-manage-subscribers","markdown":"/skills/novu-manage-subscribers.md"}},{"id":"novu-inbox-integration","name":"Novu Inbox Integration","tagline":"knock-in-app-ui twin. Feeds, not Knock guides. HMAC required in production","when":"Integrate Novu in-app Inbox (bell, feed, preferences) in React/Next/vanilla JS. knock-in-app-ui twin but feeds, not Knock guides. HMAC required in production. Distinct from knock-in-app-ui.","license":"MIT","sourceUrl":"https://github.com/novuhq/skills/blob/main/skills/inbox-integration/SKILL.md","catch":"knock-in-app-ui twin (feeds, not Knock guides). Distinct from knock-in-app-ui. HMAC required in production. Cloud Free 10k workflow runs/mo; in-app still consumes a run. OSS self-host 0 USD.","links":{"self":"/api/skills/novu-inbox-integration","html":"/skills/novu-inbox-integration","markdown":"/skills/novu-inbox-integration.md"}},{"id":"novu-manage-preferences","name":"Novu Manage Preferences","tagline":"Not Knock preferences API. Two-level model only (workflow + subscriber)","when":"Configure Novu notification preferences: workflow defaults plus subscriber overrides. Two-level model only. Not the Knock preferences API. Distinct from novu-inbox-integration UI and from knock-in-app-ui.","license":"MIT","sourceUrl":"https://github.com/novuhq/skills/blob/main/skills/manage-preferences/SKILL.md","catch":"Not Knock preferences API; two-level model only. Distinct from knock-in-app-ui and from novu-inbox-integration. readOnly hides UI; critical is the runtime bypass. Cloud Free 10k runs/mo.","links":{"self":"/api/skills/novu-manage-preferences","html":"/skills/novu-manage-preferences","markdown":"/skills/novu-manage-preferences.md"}},{"id":"novu-framework-integration","name":"Novu Framework Integration","tagline":"@novu/framework + Bridge. Cloud still executes Bridge. Not Resend-only react-email","when":"Build code-first Novu workflows with @novu/framework and a Bridge Endpoint. Cloud still executes the Bridge. Can render React Email but is not Resend-only react-email. Distinct from novu-dashboard-workflows and from react-email. HOLD novu-design-workflow. Skip connect-agent.","license":"MIT","sourceUrl":"https://github.com/novuhq/skills/blob/main/skills/framework-integration/SKILL.md","catch":"@novu/framework + Bridge; Cloud still executes Bridge. Not Resend-only react-email. Distinct from novu-dashboard-workflows and from react-email. Free 10k workflow runs/mo; over-limit does not throttle.","links":{"self":"/api/skills/novu-framework-integration","html":"/skills/novu-framework-integration","markdown":"/skills/novu-framework-integration.md"}},{"id":"novu-dashboard-workflows","name":"Novu Dashboard Workflows","tagline":"MCP/dashboard step content, not framework-integration","when":"Author step content (subject, body, editorType, conditions) for Novu Dashboard or MCP workflows. Not @novu/framework (novu-framework-integration). HOLD novu-design-workflow. Skip connect-agent.","license":"MIT","sourceUrl":"https://github.com/novuhq/skills/blob/main/skills/dashboard-workflows/SKILL.md","catch":"MCP/dashboard step content, not framework-integration. Distinct from novu-framework-integration and from knock-cli. Cloud Free 10k workflow runs/mo, no CC. OSS self-host 0 USD.","links":{"self":"/api/skills/novu-dashboard-workflows","html":"/skills/novu-dashboard-workflows","markdown":"/skills/novu-dashboard-workflows.md"}},{"id":"trigger-getting-started","name":"Trigger Getting Started","tagline":"Vendor lock. CLI login + TRIGGER_SECRET_KEY. Self-contained","when":"Bootstrap Trigger.dev into an existing project: CLI login, install @trigger.dev/sdk, write trigger.config.ts, scaffold /trigger, set TRIGGER_SECRET_KEY. Self-contained (runs before SDK install). Not Inngest setup. Distinct from trigger-authoring-tasks.","license":"Apache-2.0","sourceUrl":"https://github.com/triggerdotdev/trigger.dev/blob/main/packages/cli-v3/skills/trigger-getting-started/SKILL.md","catch":"Vendor lock. Needs CLI login + TRIGGER_SECRET_KEY from the dashboard (human steps). Free 0 USD/mo: 5 USD credits/mo, 20 concurrent runs, 10 Realtime connections, 10 schedules, 1-day logs. Do not invent hard-stop phrasing beyond Free needing an upgrade after credits. Distinct from inngest-setup.","links":{"self":"/api/skills/trigger-getting-started","html":"/skills/trigger-getting-started","markdown":"/skills/trigger-getting-started.md"}},{"id":"trigger-authoring-tasks","name":"Trigger Authoring Tasks","tagline":"CLI stub; 404s until @trigger.dev/sdk installed. False-fires on BullMQ/Inngest","when":"Write Trigger.dev tasks (task/schemaTask, retries, waits, queues, cron). CLI stub — full guide lives in node_modules/@trigger.dev/sdk and 404s until the SDK is installed. False-fires on BullMQ/Inngest. Never import the task instance into a route handler (type-only + tasks.trigger). Distinct from inngest-durable-functions.","license":"Apache-2.0","sourceUrl":"https://github.com/triggerdotdev/trigger.dev/blob/main/packages/cli-v3/skills/trigger-authoring-tasks/SKILL.md","catch":"CLI stub; 404s until @trigger.dev/sdk is installed. False-fires on BullMQ/Inngest. Never import the task instance into a route handler. Distinct from inngest-durable-functions. Free 20 concurrent runs / 5 USD credits/mo.","links":{"self":"/api/skills/trigger-authoring-tasks","html":"/skills/trigger-authoring-tasks","markdown":"/skills/trigger-authoring-tasks.md"}},{"id":"trigger-authoring-chat-agent","name":"Trigger Authoring Chat Agent","tagline":"CLI stub. Loud vs Vercel useChat / tanstack-ai-chat-experience","when":"Build durable AI chat agents with Trigger.dev chat.agent / toStreamTextOptions. CLI stub until SDK installed. Loud vs Vercel useChat and tanstack-ai-chat-experience. Forgetting ...chat.toStreamTextOptions() silently no-ops compaction/steering. Distinct from inngest-agents.","license":"Apache-2.0","sourceUrl":"https://github.com/triggerdotdev/trigger.dev/blob/main/packages/cli-v3/skills/trigger-authoring-chat-agent/SKILL.md","catch":"CLI stub. Loud vs Vercel useChat / tanstack-ai-chat-experience. Forgetting ...chat.toStreamTextOptions() silently no-ops compaction/steering. Distinct from inngest-agents. Free still 5 USD credits/mo.","links":{"self":"/api/skills/trigger-authoring-chat-agent","html":"/skills/trigger-authoring-chat-agent","markdown":"/skills/trigger-authoring-chat-agent.md"}},{"id":"trigger-chat-agent-advanced","name":"Trigger Chat Agent Advanced","tagline":"CLI stub. Version-gate. Re-POSTing /sessions drops the message","when":"Advanced Trigger.dev chat.agent patterns: sessions, human-in-the-loop, sub-agents, compaction, fast starts. CLI stub until SDK installed. Version-gate. Re-POSTing /sessions drops the message. Distinct from trigger-authoring-chat-agent basics. HOLD trigger-cost-savings.","license":"Apache-2.0","sourceUrl":"https://github.com/triggerdotdev/trigger.dev/blob/main/packages/cli-v3/skills/trigger-chat-agent-advanced/SKILL.md","catch":"CLI stub. Version-gate. Re-POSTing /sessions drops the message. Distinct from trigger-authoring-chat-agent and from inngest-agents. Free 5 USD credits/mo; do not invent hard-stop phrasing.","links":{"self":"/api/skills/trigger-chat-agent-advanced","html":"/skills/trigger-chat-agent-advanced","markdown":"/skills/trigger-chat-agent-advanced.md"}},{"id":"trigger-realtime-and-frontend","name":"Trigger Realtime and Frontend","tagline":"CLI stub. Loud vs inngest-realtime. Free cap 10 concurrent Realtime","when":"Subscribe to Trigger.dev runs from React/Next (useRealtimeRun, useTaskTrigger) and mint scoped public tokens. CLI stub until SDK installed. Loud vs inngest-realtime. createPublicToken cannot trigger — use createTriggerPublicToken. Free cap 10 concurrent Realtime connections. HOLD trigger-cost-savings.","license":"Apache-2.0","sourceUrl":"https://github.com/triggerdotdev/trigger.dev/blob/main/packages/cli-v3/skills/trigger-realtime-and-frontend/SKILL.md","catch":"CLI stub. Loud vs inngest-realtime. Free cap 10 concurrent Realtime connections. createPublicToken cannot trigger. Distinct from inngest-realtime. Free also 20 concurrent runs / 5 USD credits/mo / 1-day logs.","links":{"self":"/api/skills/trigger-realtime-and-frontend","html":"/skills/trigger-realtime-and-frontend","markdown":"/skills/trigger-realtime-and-frontend.md"}},{"id":"axiom-alerting","name":"Axiom Alerting","tagline":"v2 monitors Bearer from .axiom.toml not Knock","when":"Build Axiom v2 API monitors and alerts. Distinct from Knock Novu.","license":"MIT","sourceUrl":"https://github.com/axiomhq/skills/blob/main/skills/axiom-alerting/SKILL.md","catch":"Personal 0 USD permanent 500GB load 10 GB-hours query 25GB storage 30-day. Bearer from .axiom.toml.","links":{"self":"/api/skills/axiom-alerting","html":"/skills/axiom-alerting","markdown":"/skills/axiom-alerting.md"}},{"id":"axiom-building-dashboards","name":"Axiom Building Dashboards","tagline":"False-fires on Grafana Datadog Splunk migrate","when":"Build Axiom dashboards. False-fires on Grafana Datadog. Splunk migrate overlap with spl-to-apl.","license":"MIT","sourceUrl":"https://github.com/axiomhq/skills/blob/main/skills/axiom-building-dashboards/SKILL.md","catch":"Personal 0 USD permanent no CC. Distinct from axiom-alerting and spl-to-apl overlap note.","links":{"self":"/api/skills/axiom-building-dashboards","html":"/skills/axiom-building-dashboards","markdown":"/skills/axiom-building-dashboards.md"}},{"id":"axiom-query-metrics","name":"Axiom Query Metrics","tagline":"otel metrics v1 scripts 404 if only SKILL.md","when":"Query otel:metrics:v1 datasets with MPL. Scripts relative to skill folder 404 if only SKILL.md copied.","license":"MIT","sourceUrl":"https://github.com/axiomhq/skills/blob/main/skills/axiom-query-metrics/SKILL.md","catch":"Personal 0 USD permanent. Dataset kind otel:metrics:v1. Scripts need full skill folder not SKILL.md alone.","links":{"self":"/api/skills/axiom-query-metrics","html":"/skills/axiom-query-metrics","markdown":"/skills/axiom-query-metrics.md"}},{"id":"axiom-metrics-chart","name":"Axiom Metrics Chart","tagline":"Consumer of query-metrics zero-dep Unicode","when":"Render Axiom metrics charts. Consumer of query-metrics. Zero-dep Unicode; PNG SVG needs gnuplot.","license":"MIT","sourceUrl":"https://github.com/axiomhq/skills/blob/main/skills/axiom-metrics-chart/SKILL.md","catch":"Personal 0 USD. Zero-dep Unicode charts. PNG SVG needs gnuplot. Distinct from query-metrics.","links":{"self":"/api/skills/axiom-metrics-chart","html":"/skills/axiom-metrics-chart","markdown":"/skills/axiom-metrics-chart.md"}},{"id":"axiom-spl-to-apl","name":"Axiom SPL to APL","tagline":"Join preview 50k time pickers dont translate","when":"Translate Splunk SPL to Axiom APL. Join preview 50k rows. Time pickers do not translate. Distinct from ClickHouse MotherDuck SQL.","license":"MIT","sourceUrl":"https://github.com/axiomhq/skills/blob/main/skills/axiom-spl-to-apl/SKILL.md","catch":"Personal 0 USD permanent 30-day retention. Join preview 50k. Distinct from chdb-sql and duckdb SQL.","links":{"self":"/api/skills/axiom-spl-to-apl","html":"/skills/axiom-spl-to-apl","markdown":"/skills/axiom-spl-to-apl.md"}},{"id":"contentful-api","name":"Contentful API","tagline":"Five APIs curl-only false-fires vs JS SDK","when":"Call Contentful CMA CDA CPA Images GraphQL via curl. False-fires when they wanted JS SDK nextjs.","license":"MIT","sourceUrl":"https://github.com/contentful/skills/blob/main/skills/contentful-api/SKILL.md","catch":"MIT. Pricing not verified this pass do not invent free-tier numbers. Distinct from contentful-nextjs and sanity.","links":{"self":"/api/skills/contentful-api","html":"/skills/contentful-api","markdown":"/skills/contentful-api.md"}},{"id":"contentful-nextjs","name":"Contentful Next.js","tagline":"Next-only steals Remix Astro Nuxt vs Sanity","when":"Integrate Contentful into Next.js only. Steals Remix Astro Nuxt. Distinct from Sanity portable-text Next.","license":"MIT","sourceUrl":"https://github.com/contentful/skills/blob/main/skills/contentful-nextjs/SKILL.md","catch":"MIT. Pricing not verified this pass. Distinct from contentful-api and sanity-next.","links":{"self":"/api/skills/contentful-nextjs","html":"/skills/contentful-nextjs","markdown":"/skills/contentful-nextjs.md"}},{"id":"contentful-migration","name":"Contentful Migration","tagline":"False-fires on Prisma Drizzle vs sanity-migration","when":"Write Contentful content-model migrations. False-fires on Prisma Drizzle. Distinct from sanity-migration.","license":"MIT","sourceUrl":"https://github.com/contentful/skills/blob/main/skills/contentful-migration/SKILL.md","catch":"MIT. Pricing not verified this pass. Distinct from sanity-migration and contentful-api.","links":{"self":"/api/skills/contentful-migration","html":"/skills/contentful-migration","markdown":"/skills/contentful-migration.md"}},{"id":"contentful-custom-app-from-scratch","name":"Contentful Custom App From Scratch","tagline":"App Framework only not marketing site","when":"Scaffold Contentful App Framework custom apps with create-contentful-app. App Framework only not marketing site.","license":"MIT","sourceUrl":"https://github.com/contentful/skills/blob/main/skills/contentful-custom-app-from-scratch/SKILL.md","catch":"MIT. Pricing not verified this pass. App Framework only. HOLD enhancement guide personalization.","links":{"self":"/api/skills/contentful-custom-app-from-scratch","html":"/skills/contentful-custom-app-from-scratch","markdown":"/skills/contentful-custom-app-from-scratch.md"}},{"id":"deno-deploy","name":"Deno Deploy","tagline":"Deploy Free 1M req 20GiB egress not 100GB","when":"Deploy apps to Deno Deploy Free tier. Parent deno HOLD. Sandboxes are Pro not Free.","license":"MIT","sourceUrl":"https://github.com/denoland/skills/blob/main/skills/deno-deploy/SKILL.md","catch":"Deploy Free 1M req 20 GiB egress 10 CPU-hr 150 GiB-hr mem 10 apps 5 domains KV 1 GiB. No pause-when-over claim.","links":{"self":"/api/skills/deno-deploy","html":"/skills/deno-deploy","markdown":"/skills/deno-deploy.md"}},{"id":"deno-frontend","name":"Deno Frontend","tagline":"Next-under-Deno false-fires vs Node Next","when":"Build frontend with Deno React Vite Astro SvelteKit Next or Fresh 2.x. Parent deno HOLD.","license":"MIT","sourceUrl":"https://github.com/denoland/skills/blob/main/skills/deno-frontend/SKILL.md","catch":"Next-under-Deno false-fires vs Node Next. Fresh 2.x. Deploy Free 1M/20GiB/10 CPU-hr.","links":{"self":"/api/skills/deno-frontend","html":"/skills/deno-frontend","markdown":"/skills/deno-frontend.md"}},{"id":"migrate-to-deno","name":"Migrate to Deno","tagline":"Node runtime port false-fires","when":"Port Node apps onto Deno runtime. Parent HOLD.","license":"MIT","sourceUrl":"https://github.com/denoland/skills/blob/main/skills/migrate-to-deno/SKILL.md","catch":"Distinct from deno-frontend and deno-deploy.","links":{"self":"/api/skills/migrate-to-deno","html":"/skills/migrate-to-deno","markdown":"/skills/migrate-to-deno.md"}},{"id":"deno-sandbox","name":"Deno Sandbox","tagline":"LOUD Sandboxes not on Free Pro 20 USD","when":"Run untrusted AI code in Deno Sandboxes @deno/sandbox. Cloudflare sandbox-sdk twin. Parent deno HOLD.","license":"MIT","sourceUrl":"https://github.com/denoland/skills/blob/main/skills/deno-sandbox/SKILL.md","catch":"LOUD: Sandboxes NOT on Free. Pro 20 USD/mo. Cloudflare sandbox-sdk twin. Distinct from deno-deploy.","links":{"self":"/api/skills/deno-sandbox","html":"/skills/deno-sandbox","markdown":"/skills/deno-sandbox.md"}},{"id":"logfire-instrumentation","name":"Logfire Instrumentation","tagline":"configure vs instrument ordering silently drops traces","when":"Instrument apps with Logfire. Vendor lock. configure() vs instrument_*() ordering silently drops traces. False-fires on OTel Sentry Axiom.","license":"MIT","sourceUrl":"https://github.com/pydantic/logfire/blob/main/docs/skills/logfire-instrumentation/SKILL.md","catch":"Personal Free forever 10M records/mo hard-capped 0 USD 3 projects 1 seat 2 guests 30-day. Distinct from axiom.","links":{"self":"/api/skills/logfire-instrumentation","html":"/skills/logfire-instrumentation","markdown":"/skills/logfire-instrumentation.md"}},{"id":"logfire-query","name":"Logfire Query","tagline":"Personal Query API le 500 per day","when":"Query Logfire telemetry. Personal Query API le 500/day. False-fires on find root cause without Logfire.","license":"MIT","sourceUrl":"https://github.com/pydantic/skills/blob/main/skills/logfire-query/SKILL.md","catch":"Personal Free forever. Query API le 500/day. Distinct from instrumentation and axiom.","links":{"self":"/api/skills/logfire-query","html":"/skills/logfire-query","markdown":"/skills/logfire-query.md"}},{"id":"logfire-ui","name":"Logfire UI","tagline":"Codex-browser-shaped never-fires without browser","when":"Drive the Logfire UI. Codex-browser-shaped. Never-fires if agent has no browser.","license":"MIT","sourceUrl":"https://github.com/pydantic/skills/blob/main/skills/logfire-ui/SKILL.md","catch":"Personal Free forever. UI needs browser. Distinct from query and instrumentation.","links":{"self":"/api/skills/logfire-ui","html":"/skills/logfire-ui","markdown":"/skills/logfire-ui.md"}},{"id":"logfire-infrastructure","name":"Logfire Infrastructure","tagline":"OTel Collector no app-code false-fires on k8s","when":"Ship infra telemetry to Logfire via OTel Collector without app-code. False-fires on generic k8s postgres monitor.","license":"MIT","sourceUrl":"https://github.com/pydantic/skills/blob/main/skills/logfire-infrastructure/SKILL.md","catch":"Personal Free forever 10M records hard-capped 0 USD. Distinct from instrumentation. No plugins twins.","links":{"self":"/api/skills/logfire-infrastructure","html":"/skills/logfire-infrastructure","markdown":"/skills/logfire-infrastructure.md"}},{"id":"logfire-evals","name":"Logfire Evals","tagline":"Python-only pydantic_evals omit configure local","when":"Run Python-only pydantic_evals with Logfire. Distinct from Axiom HOLD writing-evals. Omitting logfire.configure() keeps results local.","license":"MIT","sourceUrl":"https://github.com/pydantic/skills/blob/main/skills/logfire-evals/SKILL.md","catch":"Personal Free forever. Python-only pydantic_evals. Distinct from axiom writing-evals HOLD. No plugins twins.","links":{"self":"/api/skills/logfire-evals","html":"/skills/logfire-evals","markdown":"/skills/logfire-evals.md"}},{"id":"mixpanel-tracking-implementation","name":"Mixpanel Tracking Implementation","tagline":"Vendor lock distinct from install false-fires analytics","when":"Implement Mixpanel tracking end-to-end. Vendor lock. Distinct from install. False-fires on generic add analytics.","license":"Apache-2.0","sourceUrl":"https://github.com/mixpanel/ai-plugins/blob/main/plugins/mixpanel/skills/tracking-implementation/SKILL.md","catch":"Free no trial 1M events. Over 1M Free blocks viewing reports not ingest. Distinct from PostHog.","links":{"self":"/api/skills/mixpanel-tracking-implementation","html":"/skills/mixpanel-tracking-implementation","markdown":"/skills/mixpanel-tracking-implementation.md"}},{"id":"mixpanel-create-dashboard","name":"Mixpanel Create Dashboard","tagline":"Generic slug vs axiom dashboards Engine required","when":"Build Mixpanel dashboards with Engine required. Free cap 5 saved reports per user. Distinct from axiom-building-dashboards.","license":"Apache-2.0","sourceUrl":"https://github.com/mixpanel/ai-plugins/blob/main/plugins/mixpanel/skills/create-dashboard/SKILL.md","catch":"Free 1M events 5 saved reports/user. Cohorts creatable not saved. Over 1M blocks viewing not ingest.","links":{"self":"/api/skills/mixpanel-create-dashboard","html":"/skills/mixpanel-create-dashboard","markdown":"/skills/mixpanel-create-dashboard.md"}},{"id":"mixpanel-manage-feature-flags","name":"Mixpanel Manage Feature Flags","tagline":"Not PostHog LaunchDarkly Engine required","when":"Create roll out debug Mixpanel feature flags. Not PostHog LaunchDarkly. Engine required. Do not invent Flags usage amounts.","license":"Apache-2.0","sourceUrl":"https://github.com/mixpanel/ai-plugins/blob/main/plugins/mixpanel/skills/manage-feature-flags/SKILL.md","catch":"Free no trial as long as you want. Engine required. Distinct from PostHog flags. Do not invent Flags quotas.","links":{"self":"/api/skills/mixpanel-manage-feature-flags","html":"/skills/mixpanel-manage-feature-flags","markdown":"/skills/mixpanel-manage-feature-flags.md"}},{"id":"n8n-workflow-lifecycle-official","name":"n8n Workflow Lifecycle","tagline":"Official lifecycle false-fires on ad-hoc node dumps","when":"Create activate deactivate and version n8n workflows the official way. HOLD other 8 skills.","license":"Apache-2.0","sourceUrl":"https://github.com/n8n-io/skills/blob/main/skills/n8n-workflow-lifecycle/SKILL.md","catch":"Official lifecycle. Cloud no 0 USD hobby Starter 20 EUR annual. CE self-host is 0 forever.","links":{"self":"/api/skills/n8n-workflow-lifecycle-official","html":"/skills/n8n-workflow-lifecycle-official","markdown":"/skills/n8n-workflow-lifecycle-official.md"}},{"id":"n8n-subworkflows-official","name":"n8n Subworkflows","tagline":"Official subworkflow false-fires on copy-paste nodes","when":"Extract and call reusable n8n subworkflows officially. HOLD other skills.","license":"Apache-2.0","sourceUrl":"https://github.com/n8n-io/skills/blob/main/skills/n8n-subworkflows/SKILL.md","catch":"Official subworkflows. Meter is executions. CE self-host 0 forever; Cloud Starter paid.","links":{"self":"/api/skills/n8n-subworkflows-official","html":"/skills/n8n-subworkflows-official","markdown":"/skills/n8n-subworkflows-official.md"}},{"id":"n8n-expressions-official","name":"n8n Expressions","tagline":"Expression false-fires on raw JS Code node","when":"Write n8n expressions the official way. Distinct from code-nodes. HOLD other skills.","license":"Apache-2.0","sourceUrl":"https://github.com/n8n-io/skills/blob/main/skills/n8n-expressions/SKILL.md","catch":"Official expressions vs Code node. Cloud no 0 USD hobby. CE self-host 0 forever.","links":{"self":"/api/skills/n8n-expressions-official","html":"/skills/n8n-expressions-official","markdown":"/skills/n8n-expressions-official.md"}},{"id":"n8n-loops-official","name":"n8n Loops","tagline":"Loop false-fires on SplitInBatches misuse","when":"Build official n8n loops and batching. HOLD other skills.","license":"Apache-2.0","sourceUrl":"https://github.com/n8n-io/skills/blob/main/skills/n8n-loops/SKILL.md","catch":"Official loops. Distinct from expressions and code-nodes. CE self-host 0 forever.","links":{"self":"/api/skills/n8n-loops-official","html":"/skills/n8n-loops-official","markdown":"/skills/n8n-loops-official.md"}},{"id":"n8n-code-nodes-official","name":"n8n Code Nodes","tagline":"JS/Python Code node false-fires on expressions","when":"Use n8n Code nodes in JS or Python officially. Distinct from expressions. HOLD other skills.","license":"Apache-2.0","sourceUrl":"https://github.com/n8n-io/skills/blob/main/skills/n8n-code-nodes/SKILL.md","catch":"Official Code nodes. Trial 1000 exec 5 concurrent 180s. CE self-host 0 forever.","links":{"self":"/api/skills/n8n-code-nodes-official","html":"/skills/n8n-code-nodes-official","markdown":"/skills/n8n-code-nodes-official.md"}},{"id":"twilio-send-message","name":"Twilio Send Message","tagline":"Vendor lock trial PAYG steal vs Knock Novu","when":"Send SMS MMS WhatsApp via Twilio Programmable Messaging. WhatsApp 24-hour window. Distinct from Knock Novu Resend. HOLD sms/whatsapp split skills.","license":"MIT","sourceUrl":"https://github.com/twilio/ai/blob/main/skills/twilio-send-message/SKILL.md","catch":"No 0 USD hobby. Official trial 30 days no CC then PAYG. Geo-limited templates not custom bodies. Distinct from Knock Novu.","links":{"self":"/api/skills/twilio-send-message","html":"/skills/twilio-send-message","markdown":"/skills/twilio-send-message.md"}},{"id":"twilio-verify-send-otp","name":"Twilio Verify Send OTP","tagline":"Verify product not Programmable Messaging","when":"Send OTPs with Twilio Verify not Programmable Messaging. Distinct from Infisical. Trial verified-number cap makes OTP loops fail closed.","license":"MIT","sourceUrl":"https://github.com/twilio/ai/blob/main/skills/twilio-verify-send-otp/SKILL.md","catch":"Verify product. Trial 30 days then PAYG. Verified-number cap fails closed. Do not invent max 5 recipients.","links":{"self":"/api/skills/twilio-verify-send-otp","html":"/skills/twilio-verify-send-otp","markdown":"/skills/twilio-verify-send-otp.md"}},{"id":"twilio-voice-outbound-calls","name":"Twilio Voice Outbound Calls","tagline":"Irreversible charged TCPA quiet hours","when":"Place outbound Twilio Voice calls. Irreversible and charged. TCPA quiet hours. Distinct from TwiML skill.","license":"MIT","sourceUrl":"https://github.com/twilio/ai/blob/main/skills/twilio-voice-outbound-calls/SKILL.md","catch":"Trial 30 days then PAYG. Charged irreversible. TCPA quiet hours. Distinct from twilio-voice-twiml.","links":{"self":"/api/skills/twilio-voice-outbound-calls","html":"/skills/twilio-voice-outbound-calls","markdown":"/skills/twilio-voice-outbound-calls.md"}},{"id":"twilio-voice-twiml","name":"Twilio Voice TwiML","tagline":"Webhook TwiML not REST dial pair outbound","when":"Serve webhook TwiML for Voice not REST dial. Pair with twilio-voice-outbound-calls.","license":"MIT","sourceUrl":"https://github.com/twilio/ai/blob/main/skills/twilio-voice-twiml/SKILL.md","catch":"Trial 30 days then PAYG. Webhook TwiML not REST dial. Distinct from outbound-calls and Studio.","links":{"self":"/api/skills/twilio-voice-twiml","html":"/skills/twilio-voice-twiml","markdown":"/skills/twilio-voice-twiml.md"}},{"id":"twilio-studio-flows","name":"Twilio Studio Flows","tagline":"Visual Studio vs TwiML code distinct from n8n","when":"Build Twilio Studio visual flows. Visual Studio vs TwiML or code. Distinct from n8n workflows.","license":"MIT","sourceUrl":"https://github.com/twilio/ai/blob/main/skills/twilio-studio-flows/SKILL.md","catch":"Trial 30 days then PAYG. Visual Studio vs TwiML. Distinct from n8n and voice-twiml. No ~45 dump.","links":{"self":"/api/skills/twilio-studio-flows","html":"/skills/twilio-studio-flows","markdown":"/skills/twilio-studio-flows.md"}},{"id":"saleor-core","name":"Saleor Core","tagline":"Internals encyclopedia version-gate 3.23 not getting-started","when":"Saleor backend internals encyclopedia. Version-gate 3.23+. Not getting-started. Distinct from Shopify Contentful Sanity.","license":"BSD-3-Clause","sourceUrl":"https://github.com/saleor/agent-skills/blob/main/skills/saleor-core/SKILL.md","catch":"Repo LICENSE is BSD-3-Clause skill YAML says MIT use LICENSE file. OSS free personal plus commercial. Do not invent Cloud quote pricing.","links":{"self":"/api/skills/saleor-core","html":"/skills/saleor-core","markdown":"/skills/saleor-core.md"}},{"id":"saleor-app","name":"Saleor App","tagline":"Next.js examples claim framework-agnostic vs Contentful App","when":"Build Saleor apps protocol manifest appbridge webhooks. Next.js examples but claims framework-agnostic. Distinct from Contentful App Framework.","license":"BSD-3-Clause","sourceUrl":"https://github.com/saleor/agent-skills/blob/main/skills/saleor-app/SKILL.md","catch":"Repo LICENSE BSD-3-Clause not skill YAML MIT. OSS free. Distinct from contentful-custom-app-from-scratch.","links":{"self":"/api/skills/saleor-app","html":"/skills/saleor-app","markdown":"/skills/saleor-app.md"}},{"id":"saleor-configurator","name":"Saleor Configurator","tagline":"Store config as code vs Contentful migration scripts","when":"Manage Saleor store configuration as code. Distinct from Contentful migration scripts. HOLD storefront-builder.","license":"BSD-3-Clause","sourceUrl":"https://github.com/saleor/agent-skills/blob/main/skills/saleor-configurator/SKILL.md","catch":"Repo LICENSE BSD-3-Clause. OSS free personal plus commercial. Distinct from contentful-migration. Do not invent Cloud pricing.","links":{"self":"/api/skills/saleor-configurator","html":"/skills/saleor-configurator","markdown":"/skills/saleor-configurator.md"}},{"id":"saleor-storefront","name":"Saleor Storefront","tagline":"GraphQL products checkout channels not Next starter","when":"Saleor GraphQL storefront API products checkout channels. Framework-agnostic API not Next starter. HOLD storefront-builder.","license":"BSD-3-Clause","sourceUrl":"https://github.com/saleor/agent-skills/blob/main/skills/saleor-storefront/SKILL.md","catch":"Repo LICENSE BSD-3-Clause. OSS free. Framework-agnostic GraphQL not Next starter. Distinct from Shopify.","links":{"self":"/api/skills/saleor-storefront","html":"/skills/saleor-storefront","markdown":"/skills/saleor-storefront.md"}},{"id":"loops-api","name":"Loops API","tagline":"Five product surfaces in one vendor lock","when":"Use Loops API across five product surfaces in one skill. Vendor lock. Distinct from resend-cli react-email and n8n-loops-official.","license":"MIT","sourceUrl":"https://github.com/loops-so/skills/blob/main/skills/loops-api/SKILL.md","catch":"Free up to 4000 sends/month Powered by Loops footer all features no CC. 1000 stored subscribed contacts is slider default. Distinct from n8n-loops-official.","links":{"self":"/api/skills/loops-api","html":"/skills/loops-api","markdown":"/skills/loops-api.md"}},{"id":"loops-cli","name":"Loops CLI","tagline":"Overlaps loops-api distinct from resend-cli","when":"Use Loops CLI from the terminal. Overlaps loops-api. Distinct from resend-cli. HOLD email-sending-best-practices.","license":"MIT","sourceUrl":"https://github.com/loops-so/skills/blob/main/skills/loops-cli/SKILL.md","catch":"Free 4000 sends/month no CC. Distinct from resend-cli and loops-api. HOLD loops-email-sending-best-practices.","links":{"self":"/api/skills/loops-cli","html":"/skills/loops-cli","markdown":"/skills/loops-cli.md"}},{"id":"loops-lmx","name":"Loops LMX","tagline":"False-fires on generic welcome email React Email","when":"Write and review Loops Markup Language email bodies. False-fires on generic welcome email or React Email.","license":"MIT","sourceUrl":"https://github.com/loops-so/skills/blob/main/skills/loops-lmx/SKILL.md","catch":"Free 4000 sends/month Powered by Loops footer. Distinct from react-email. False-fires on generic welcome email.","links":{"self":"/api/skills/loops-lmx","html":"/skills/loops-lmx","markdown":"/skills/loops-lmx.md"}},{"id":"temporal-developer","name":"Temporal Developer","tagline":"Vendor lock + always-on-adjacent. start-dev is not production","when":"Build Temporal workflows, activities, and workers (Python/TS/Go/Java/.NET/Ruby/Rust), CLI, non-determinism, signals/queries. Distinct from inngest-durable-functions and trigger-authoring-tasks.","license":"MIT","sourceUrl":"https://github.com/temporalio/skill-temporal-developer/blob/main/SKILL.md","catch":"Vendor lock + always-on-adjacent on any durable workflow. Local `temporal server start-dev` is not production. OSS self-host $0. Distinct from inngest-durable-functions / trigger-authoring-tasks.","links":{"self":"/api/skills/temporal-developer","html":"/skills/temporal-developer","markdown":"/skills/temporal-developer.md"}},{"id":"temporal-ops","name":"Temporal Ops","tagline":"CLI ops not SDK. Names temporal-workertuning. False-fires generic TLS/gRPC","when":"Administer Temporal Cloud or self-hosted via CLI (namespaces, certs, batch cancel/reset, billing, SAML/SCIM) — not SDK code.","license":"MIT","sourceUrl":"https://github.com/temporalio/skill-temporal-ops/blob/main/SKILL.md","catch":"Names temporal-workertuning sibling (do not invent/dump). False-fires on generic TLS/gRPC. Cloud ops paths need paid Cloud. OSS self-host $0. Cloud not hobby.","links":{"self":"/api/skills/temporal-ops","html":"/skills/temporal-ops","markdown":"/skills/temporal-ops.md"}},{"id":"temporal-cloud","name":"Temporal Cloud","tagline":"Cloud-only. Not $0 — $1,000 credits expire 90 days then Essentials","when":"Temporal Cloud connect/auth/x509/namespace/PrivateLink/no pollers/RESOURCE_EXHAUSTED.","license":"MIT","sourceUrl":"https://github.com/temporalio/skills-temporal-cloud/blob/main/SKILL.md","catch":"Cloud-only. Loud: not $0 — $1,000 credits expire 90 days, then Essentials greater of $100/mo or 5% of usage. CC required for Cloud; OSS quickstart no CC. Keep with Catch (OSS path is developer/ops). Do not HOLD as paid-only. Distinct from Inngest/Trigger/Loops/n8n-loops-official.","links":{"self":"/api/skills/temporal-cloud","html":"/skills/temporal-cloud","markdown":"/skills/temporal-cloud.md"}},{"id":"appwrite-cli","name":"Appwrite CLI","tagline":"CLI/config/CI not SDK. Cloud Free pauses after 1 week Console inactivity","when":"Use Appwrite CLI for config, pull/push, CI, generate/types. Not SDK code. HOLD swift, go/dotnet/php/ruby/rust, deploy-function, deploy-site.","license":"BSD-3-Clause","sourceUrl":"https://github.com/appwrite/skills/blob/main/skills/appwrite-cli/SKILL.md","catch":"Cloud Free $0 pauses after 1 week Console inactivity; 2 projects, 2 functions/project. OSS self-host $0 production path. Not SDK. Distinct from supabase/convex/neon. HOLD swift go/dotnet/php/ruby/rust deploy-function deploy-site.","links":{"self":"/api/skills/appwrite-cli","html":"/skills/appwrite-cli","markdown":"/skills/appwrite-cli.md"}},{"id":"appwrite-typescript","name":"Appwrite TypeScript","tagline":"Web/RN/Node-Deno. TablesDB not deprecated Databases","when":"Build Appwrite apps in web, React Native, or Node/Deno. TablesDB not deprecated Databases. Distinct from supabase JS.","license":"BSD-3-Clause","sourceUrl":"https://github.com/appwrite/skills/blob/main/skills/appwrite-typescript/SKILL.md","catch":"TablesDB not deprecated Databases. Distinct from supabase JS. Cloud Free $0 pauses after 1 week Console inactivity; 2 projects, 2 functions/project. OSS self-host $0.","links":{"self":"/api/skills/appwrite-typescript","html":"/skills/appwrite-typescript","markdown":"/skills/appwrite-typescript.md"}},{"id":"appwrite-dart","name":"Appwrite Dart","tagline":"Flutter or server Dart. Distinct from supabase-flutter","when":"Build Flutter or server Dart with Appwrite. Distinct from supabase-flutter.","license":"BSD-3-Clause","sourceUrl":"https://github.com/appwrite/skills/blob/main/skills/appwrite-dart/SKILL.md","catch":"Distinct from supabase-flutter. Cloud Free $0 pauses after 1 week Console inactivity; 2 projects, 2 functions/project. OSS self-host $0.","links":{"self":"/api/skills/appwrite-dart","html":"/skills/appwrite-dart","markdown":"/skills/appwrite-dart.md"}},{"id":"appwrite-python","name":"Appwrite Python","tagline":"Django/Flask/FastAPI server SDK. Server-only no browser","when":"Use Appwrite Python server SDK in Django, Flask, or FastAPI. Server-only, no browser. Distinct from supabase-py.","license":"BSD-3-Clause","sourceUrl":"https://github.com/appwrite/skills/blob/main/skills/appwrite-python/SKILL.md","catch":"Server-only no browser. Distinct from supabase-py. Cloud Free $0 pauses after 1 week Console inactivity; 2 projects, 2 functions/project. OSS self-host $0.","links":{"self":"/api/skills/appwrite-python","html":"/skills/appwrite-python","markdown":"/skills/appwrite-python.md"}},{"id":"appwrite-kotlin","name":"Appwrite Kotlin","tagline":"Android or Kotlin/JVM. Activity OAuth/coroutines. Not Swift/KMP","when":"Build native Android or Kotlin/JVM with Appwrite. Activity OAuth and coroutines. Not Swift/KMP.","license":"BSD-3-Clause","sourceUrl":"https://github.com/appwrite/skills/blob/main/skills/appwrite-kotlin/SKILL.md","catch":"Not Swift/KMP. Activity OAuth/coroutines. Cloud Free $0 pauses after 1 week Console inactivity; 2 projects, 2 functions/project. Distinct from supabase/convex/neon. OSS self-host $0.","links":{"self":"/api/skills/appwrite-kotlin","html":"/skills/appwrite-kotlin","markdown":"/skills/appwrite-kotlin.md"}},{"id":"stream-builder","name":"Stream Builder","tagline":"Only when named. Do not auto-select. Web React defaults to stream-react","when":"Use only when the user names stream-builder or /stream-builder. Do NOT auto-select. Web React defaults to stream-react.","license":"Apache-2.0","sourceUrl":"https://github.com/GetStream/agent-skills/blob/main/skills/stream-builder/SKILL.md","catch":"Do not auto-select. Web React defaults to stream-react. Chat Free 1,000 MAU, 100 concurrent, no CC. Do not invent Video/Feeds caps. HOLD stream parent, stream-docs, android/swift/unity/unreal.","links":{"self":"/api/skills/stream-builder","html":"/skills/stream-builder","markdown":"/skills/stream-builder.md"}},{"id":"stream-feeds-migration","name":"Stream Feeds Migration","tagline":"Feeds v2 to v3. Version-gate. Needs live v2 key+secret. Stale when v2 is gone","when":"Generate Activity Feeds v2 to v3 sync mapping. Version-gate. Needs live v2 key+secret. Stale the day v2 is gone.","license":"Apache-2.0","sourceUrl":"https://github.com/GetStream/agent-skills/blob/main/skills/stream-feeds-migration/SKILL.md","catch":"Version-gate. Needs live v2 key+secret. Stale the day v2 is gone. Do not invent Video/Feeds caps. Distinct from stream-react Feeds path.","links":{"self":"/api/skills/stream-feeds-migration","html":"/skills/stream-feeds-migration","markdown":"/skills/stream-feeds-migration.md"}},{"id":"stream-react","name":"Stream React","tagline":"Steals generic chat app. Web only not RN. Distinct from livekit-agents Knock Novu","when":"Build React/Next Chat+Video+Feeds+Moderation. Steals generic chat app. Web only, not RN. Distinct from livekit-agents / Knock/Novu.","license":"Apache-2.0","sourceUrl":"https://github.com/GetStream/agent-skills/blob/main/skills/stream-react/SKILL.md","catch":"Steals generic chat app. Web only not RN. Distinct from livekit-agents / knock-in-app-ui / novu-inbox-integration. Chat Free 1,000 MAU, 100 concurrent, no CC. Do not invent Video/Feeds caps.","links":{"self":"/api/skills/stream-react","html":"/skills/stream-react","markdown":"/skills/stream-react.md"}},{"id":"stream-react-native","name":"Stream React Native","tagline":"RN CLI/Expo. New Architecture required. Distinct from stream-react","when":"Build Stream Chat/Video/Feeds in React Native CLI or Expo. New Architecture required. Distinct from stream-react.","license":"Apache-2.0","sourceUrl":"https://github.com/GetStream/agent-skills/blob/main/skills/stream-react-native/SKILL.md","catch":"New Architecture required. Distinct from stream-react. Chat Free 1,000 MAU, 100 concurrent, no CC. Do not invent Video/Feeds caps.","links":{"self":"/api/skills/stream-react-native","html":"/skills/stream-react-native","markdown":"/skills/stream-react-native.md"}},{"id":"stream-flutter","name":"Stream Flutter","tagline":"Flutter Chat/Video/Feeds. Feeds has no pre-built UI. Distinct from appwrite-dart","when":"Build Stream Chat/Video/Feeds in Flutter. Feeds has no pre-built UI. Distinct from appwrite-dart.","license":"Apache-2.0","sourceUrl":"https://github.com/GetStream/agent-skills/blob/main/skills/stream-flutter/SKILL.md","catch":"Feeds has no pre-built UI. Distinct from appwrite-dart. Chat Free 1,000 MAU, 100 concurrent, no CC. Do not invent Video/Feeds caps.","links":{"self":"/api/skills/stream-flutter","html":"/skills/stream-flutter","markdown":"/skills/stream-flutter.md"}},{"id":"mlflow-onboarding","name":"MLflow Onboarding","tagline":"GenAI vs classic ML get-started router","when":"Get started or add MLflow — GenAI vs classic ML tutorial paths.","license":"Apache-2.0","sourceUrl":"https://github.com/mlflow/skills/blob/main/mlflow-onboarding/SKILL.md","catch":"Router-adjacent (picks tutorials). False-fires on generic add observability. Distinct from logfire-instrumentation. OSS self-host $0. Do not reprint Databricks managed DBU.","links":{"self":"/api/skills/mlflow-onboarding","html":"/skills/mlflow-onboarding","markdown":"/skills/mlflow-onboarding.md"}},{"id":"mlflow-instrumenting-tracing","name":"MLflow Instrumenting Tracing","tagline":"Add MLflow Tracing across Python/TS agent stacks","when":"Add MLflow Tracing (Python/TS; LangGraph/LangChain/OpenAI/DSPy/CrewAI). Must-load before agent-evaluation (that sibling is HOLD).","license":"Apache-2.0","sourceUrl":"https://github.com/mlflow/skills/blob/main/instrumenting-with-mlflow-tracing/SKILL.md","catch":"Vendor lock vs live logfire-instrumentation. HOLD agent-evaluation sibling. OSS self-host $0.","links":{"self":"/api/skills/mlflow-instrumenting-tracing","html":"/skills/mlflow-instrumenting-tracing","markdown":"/skills/mlflow-instrumenting-tracing.md"}},{"id":"mlflow-retrieving-traces","name":"MLflow Retrieving Traces","tagline":"Search/filter traces by ID, status, tags, latency","when":"Get/search/filter MLflow traces by ID/status/tags/latency.","license":"Apache-2.0","sourceUrl":"https://github.com/mlflow/skills/blob/main/retrieving-mlflow-traces/SKILL.md","catch":"Fetch/search, not analysis — pair with mlflow-analyzing-trace.","links":{"self":"/api/skills/mlflow-retrieving-traces","html":"/skills/mlflow-retrieving-traces","markdown":"/skills/mlflow-retrieving-traces.md"}},{"id":"mlflow-analyzing-trace","name":"MLflow Analyzing Trace","tagline":"One trace ID for debug, RCA, quality","when":"One MLflow trace ID — debug, RCA, or quality review.","license":"Apache-2.0","sourceUrl":"https://github.com/mlflow/skills/blob/main/analyze-mlflow-trace/SKILL.md","catch":"Twin-adjacent to retrieving (search vs one ID). Generic root-cause steal.","links":{"self":"/api/skills/mlflow-analyzing-trace","html":"/skills/mlflow-analyzing-trace","markdown":"/skills/mlflow-analyzing-trace.md"}},{"id":"mlflow-querying-metrics","name":"MLflow Querying Metrics","tagline":"Aggregated token/latency/count from tracking server","when":"Aggregated token/latency/count/quality metrics from an MLflow tracking server.","license":"Apache-2.0","sourceUrl":"https://github.com/mlflow/skills/blob/main/querying-mlflow-metrics/SKILL.md","catch":"Ships fetch_metrics.py beside SKILL.md. Distinct from logfire-query and axiom-query-metrics (MLflow tracking server, not Logfire OTel / APL).","links":{"self":"/api/skills/mlflow-querying-metrics","html":"/skills/mlflow-querying-metrics","markdown":"/skills/mlflow-querying-metrics.md"}},{"id":"wandb-primary","name":"W&B Primary","tagline":"Mixed runs, artifacts, Weave, Reports, Launch","when":"Mixed Weights & Biases work — runs, artifacts, Weave traces, Reports, Launch.","license":"Apache-2.0","sourceUrl":"https://github.com/wandb/skills/blob/main/skills/wandb-primary/SKILL.md","catch":"Parent/always-on (what’s happening in this W&B project). Loud: Personal Free $0/mo for personal AI apps/models (up to 5 model seats, 5 GB/mo storage, 1 GB/mo Weave ingestion) but corporate use is not allowed. Do not invent Weave-seat numbers. Distinct from mlflow-onboarding.","links":{"self":"/api/skills/wandb-primary","html":"/skills/wandb-primary","markdown":"/skills/wandb-primary.md"}},{"id":"wandb-autoresearch","name":"W&B Autoresearch","tagline":"Bounded training research via W&B Launch","when":"Bounded training research via W&B Launch (queues, serial trials, resumable state).","license":"Apache-2.0","sourceUrl":"https://github.com/wandb/skills/blob/main/skills/wandb-autoresearch/SKILL.md","catch":"Launch-only — must not substitute local wandb.init() for Launch compute. Vendor lock. Distinct from MLflow tracing.","links":{"self":"/api/skills/wandb-autoresearch","html":"/skills/wandb-autoresearch","markdown":"/skills/wandb-autoresearch.md"}},{"id":"wandb-eval-tables","name":"W&B Eval Tables","tagline":"Non-destructive EvalTable previews from wandb.Table","when":"Convert wandb.Table artifacts to non-destructive EvalTable previews.","license":"Apache-2.0","sourceUrl":"https://github.com/wandb/skills/blob/main/skills/wandb-eval-tables/SKILL.md","catch":"Creates new runs/keys; never overwrites source. Distinct from logfire-evals and HOLD mlflow agent-evaluation.","links":{"self":"/api/skills/wandb-eval-tables","html":"/skills/wandb-eval-tables","markdown":"/skills/wandb-eval-tables.md"}},{"id":"minio-mc","name":"MinIO mc","tagline":"AIStor mc CLI for S3-compatible storage","when":"AIStor mc CLI against S3-compatible storage (alias, ls/cp, versioning, replication, Tables).","license":"Apache-2.0","sourceUrl":"https://github.com/minio/skills/blob/main/mc/SKILL.md","catch":"Targets AIStor — github.com/minio/minio is archived. Requires mc on PATH. Destructive ops. Works against AWS S3 too (false-fire vs AWS CLI). Distinct from neon-object-storage. AIStor Free $0 standalone/single-node only (no distributed HA).","links":{"self":"/api/skills/minio-mc","html":"/skills/minio-mc","markdown":"/skills/minio-mc.md"}},{"id":"minio-aimem","name":"MinIO AIMem","tagline":"AIStor Memory FUSE workspace for a remote bucket","when":"Inside an AIStor Memory FUSE workspace (POSIX reads/writes to a remote bucket).","license":"Apache-2.0","sourceUrl":"https://github.com/minio/skills/blob/main/aimem/SKILL.md","catch":"Never-fires unless that mount exists. Not generic agent memory. Targets AIStor — minio/minio archived.","links":{"self":"/api/skills/minio-aimem","html":"/skills/minio-aimem","markdown":"/skills/minio-aimem.md"}},{"id":"minio-docs","name":"MinIO Docs","tagline":"ISO 24495-1 plain-language README/guides","when":"Writing README/guides to ISO 24495-1 Plain Language for MinIO/AIStor.","license":"Apache-2.0","sourceUrl":"https://github.com/minio/skills/blob/main/docs/SKILL.md","catch":"Always-on docs steal (same class as wandb-primary). Kept with Catch so this is not a 2-drip. Targets AIStor — minio/minio archived. HOLD pr-autofix.","links":{"self":"/api/skills/minio-docs","html":"/skills/minio-docs","markdown":"/skills/minio-docs.md"}},{"id":"tigris-object-operations","name":"Tigris Object Operations","tagline":"put/get/remove/list/head/presigned via @tigrisdata/storage","when":"Put/get/remove/list/head/presigned objects with native @tigrisdata/storage.","license":"MIT","sourceUrl":"https://github.com/tigrisdata/skills/blob/main/skills/tigris-object-operations/SKILL.md","catch":"Vendor lock native @tigrisdata/storage not boto3. Distinct from minio-mc. False-fires on generic upload. Overlaps HOLD file-storage. Free 5GB Standard + 10k Class A + 100k Class B/mo, no CC, egress 0. Do not reprint PAYG.","links":{"self":"/api/skills/tigris-object-operations","html":"/skills/tigris-object-operations","markdown":"/skills/tigris-object-operations.md"}},{"id":"tigris-bucket-management","name":"Tigris Bucket Management","tagline":"Create/list/inspect/delete with Tigris snapshot/fork fields","when":"Create/list/inspect/delete buckets (access, region, snapshot enable, fork source).","license":"MIT","sourceUrl":"https://github.com/tigrisdata/skills/blob/main/skills/tigris-bucket-management/SKILL.md","catch":"enableSnapshot/sourceBucketSnapshot is Tigris-only, not S3 CreateBucket. Distinct from minio-mc mb.","links":{"self":"/api/skills/tigris-bucket-management","html":"/skills/tigris-bucket-management","markdown":"/skills/tigris-bucket-management.md"}},{"id":"tigris-s3-migration","name":"Tigris S3 Migration","tagline":"Shadow-bucket/drain from S3, GCS, or Azure Blob","when":"Shadow-bucket/drain migration from AWS S3, GCS, or Azure Blob into Tigris.","license":"MIT","sourceUrl":"https://github.com/tigrisdata/skills/blob/main/skills/tigris-s3-migration/SKILL.md","catch":"Vendor steal vs rclone/mc mirror. Not a MinIO to AIStor path. Does not cover OSS MinIO EOL.","links":{"self":"/api/skills/tigris-s3-migration","html":"/skills/tigris-s3-migration","markdown":"/skills/tigris-s3-migration.md"}},{"id":"tigris-snapshots-forking","name":"Tigris Snapshots Forking","tagline":"Whole-bucket PITR and copy-on-write forks","when":"Whole-bucket point-in-time recovery and copy-on-write forks.","license":"MIT","sourceUrl":"https://github.com/tigrisdata/skills/blob/main/skills/tigris-snapshots-forking/SKILL.md","catch":"Not S3 object versioning. Distinct from HOLD snapshots-recovery. False-fires on git/Neon/Postgres fork.","links":{"self":"/api/skills/tigris-snapshots-forking","html":"/skills/tigris-snapshots-forking","markdown":"/skills/tigris-snapshots-forking.md"}},{"id":"tigris-agent-kit","name":"Tigris Agent Kit","tagline":"tigrisdata agent-kit forks, TTL workspaces, checkpoints","when":"Use tigrisdata agent-kit for forks, TTL workspaces, checkpoints, and bucket-webhook.","license":"MIT","sourceUrl":"https://github.com/tigrisdata/skills/blob/main/skills/tigris-agent-kit/SKILL.md","catch":"Not generic agent storage. Overlaps snapshots-forking compose layer. Distinct from minio-aimem. Extra package manager package.","links":{"self":"/api/skills/tigris-agent-kit","html":"/skills/tigris-agent-kit","markdown":"/skills/tigris-agent-kit.md"}},{"id":"tigris-lifecycle-management","name":"Tigris Lifecycle Management","tagline":"Expiration, TTL delete, Standard to IA/Archive","when":"Object expiration, TTL delete, and Standard to IA/Archive transitions.","license":"MIT","sourceUrl":"https://github.com/tigrisdata/skills/blob/main/skills/tigris-lifecycle-management/SKILL.md","catch":"Free allowance is Standard 5 GB only. IA 30-day / Archive 90-day min retention still bills if TTL fires early. Distinct from object-ops remove. Do not reprint PAYG rates.","links":{"self":"/api/skills/tigris-lifecycle-management","html":"/skills/tigris-lifecycle-management","markdown":"/skills/tigris-lifecycle-management.md"}},{"id":"yugabyte-ysql","name":"YugabyteDB YSQL","tagline":"SQL/schema on YSQL port 5433 with shard keys","when":"SQL/schema on YSQL (port 5433) — sharding, smart drivers, txn retries, PG migration.","license":"Apache-2.0","sourceUrl":"https://github.com/yugabyte/skills/blob/main/skills/ysql/SKILL.md","catch":"Vendor lock to YB, not vanilla Postgres. Distinct from neon-postgres (HASH shard keys, 5433 not 5432, no Neon branches). False-fires on generic CREATE TABLE. OSS self-host Apache-2.0 $0. Aeon Sandbox Free: 1 node / <=2 vCPU / 4 GB RAM / 10 GB / 15 connections; paused after 10 days inactivity, deleted after 15. Do not reprint Aeon Dedicated $/vCPU.","links":{"self":"/api/skills/yugabyte-ysql","html":"/skills/yugabyte-ysql","markdown":"/skills/yugabyte-ysql.md"}},{"id":"yugabyte-ycql","name":"YugabyteDB YCQL","tagline":"CQL schema on YCQL port 9042","when":"CQL schema on YCQL (port 9042).","license":"Apache-2.0","sourceUrl":"https://github.com/yugabyte/skills/blob/main/skills/ycql/SKILL.md","catch":"Not Apache Cassandra. YCQL secondary indexes are global + ACID. Distinct from yugabyte-ysql. OSS self-host Apache-2.0 $0.","links":{"self":"/api/skills/yugabyte-ycql","html":"/skills/yugabyte-ycql","markdown":"/skills/yugabyte-ycql.md"}},{"id":"yugabyte-rag-langchain","name":"YugabyteDB RAG LangChain","tagline":"Hybrid vector+FTS via LangChain PGVectorStore","when":"RAG / hybrid vector+FTS with LangChain PGVectorStore on YugabyteDB.","license":"Apache-2.0","sourceUrl":"https://github.com/yugabyte/skills/blob/main/skills/yb-rag-langchain/SKILL.md","catch":"Not Pinecone/Qdrant. ANN is ybhnsw; IVFFlat unsupported. PGVectorStore v2 not v1. HybridSearchConfig top_k defaults to 4.","links":{"self":"/api/skills/yugabyte-rag-langchain","html":"/skills/yugabyte-rag-langchain","markdown":"/skills/yugabyte-rag-langchain.md"}},{"id":"yugabyte-k8s-operator","name":"YugabyteDB K8s Operator","tagline":"YBUniverse CRDs / Helm on Kubernetes","when":"YBUniverse CRDs / Helm on Kubernetes for YugabyteDB.","license":"Apache-2.0","sourceUrl":"https://github.com/yugabyte/skills/blob/main/skills/yb-k8s-operator/SKILL.md","catch":"Loud: folder yb-k8s-operator, frontmatter name is operator. Body covers YBA Kubernetes Operator (commercial) and does not fully apply to the YugabyteDB OSS Kubernetes Operator. Will prescribe YBA CRDs the OSS operator does not have.","links":{"self":"/api/skills/yugabyte-k8s-operator","html":"/skills/yugabyte-k8s-operator","markdown":"/skills/yugabyte-k8s-operator.md"}},{"id":"redpanda-streaming","name":"Redpanda Streaming","tagline":"Produce/consume on Redpanda Kafka API :9092","when":"Produce/consume, consumer groups, transactions, topic config, Kafka client compatibility on Redpanda (Kafka API :9092).","license":"Apache-2.0","sourceUrl":"https://github.com/redpanda-data/skills/blob/main/skills/streaming/SKILL.md","catch":"Not Apache Kafka/MSK. Skills Apache-2.0; Redpanda Community is BSL 1.1 (free source-available; cannot offer as commercial streaming service; converts to Apache-2.0 four years after each merge). Self-host Community $0. Iceberg/Cloud Topics/Tiered Storage here are Enterprise-licensed, not the $0 path. Distinct from GetStream/LiveKit.","links":{"self":"/api/skills/redpanda-streaming","html":"/skills/redpanda-streaming","markdown":"/skills/redpanda-streaming.md"}},{"id":"redpanda-rpk-topic","name":"Redpanda rpk Topic","tagline":"Create/alter/produce/consume via rpk topic","when":"Create/alter/produce/consume topics via rpk topic.","license":"Apache-2.0","sourceUrl":"https://github.com/redpanda-data/skills/blob/main/skills/rpk-topic/SKILL.md","catch":"rpk, not kafka-topics.sh. Overlaps streaming (this is the CLI). Distinct from minio-mc. Community BSL self-host $0.","links":{"self":"/api/skills/redpanda-rpk-topic","html":"/skills/redpanda-rpk-topic","markdown":"/skills/redpanda-rpk-topic.md"}},{"id":"redpanda-rpk-transform","name":"Redpanda rpk Transform","tagline":"In-broker Wasm transforms via rpk transform","when":"In-broker Wasm transforms (TinyGo/Rust/JS/TS) via rpk transform.","license":"Apache-2.0","sourceUrl":"https://github.com/redpanda-data/skills/blob/main/skills/rpk-transform/SKILL.md","catch":"Not Kafka Streams/Flink/Connect. data_transforms_enabled triggers a rolling restart. TinyGo default: no goroutines. No network/disk inside Wasm. Not on Serverless (BYOC/Dedicated only).","links":{"self":"/api/skills/redpanda-rpk-transform","html":"/skills/redpanda-rpk-transform","markdown":"/skills/redpanda-rpk-transform.md"}},{"id":"redpanda-connect","name":"Redpanda Connect","tagline":"Declarative YAML pipelines (ex-Benthos) via rpk connect","when":"Declarative YAML pipelines (ex-Benthos) with rpk connect run / Bloblang.","license":"Apache-2.0","sourceUrl":"https://github.com/redpanda-data/skills/blob/main/skills/connect/SKILL.md","catch":"Community $0 BSL; enterprise connectors blocked without a license after the Connect 30-day trial. Not the CDC dump (HOLD connect-cdc-*).","links":{"self":"/api/skills/redpanda-connect","html":"/skills/redpanda-connect","markdown":"/skills/redpanda-connect.md"}},{"id":"redpanda-rpk-redpanda","name":"Redpanda rpk Redpanda","tagline":"Self-managed broker lifecycle via rpk redpanda","when":"Self-managed broker lifecycle (rpk redpanda start/stop/tune, redpanda.yaml).","license":"Apache-2.0","sourceUrl":"https://github.com/redpanda-data/skills/blob/main/skills/rpk-redpanda/SKILL.md","catch":"Self-managed only — hidden on macOS/Windows rpk builds; does not apply to Cloud. This is the $0 Community BSL path. Distinct from cloud-serverless.","links":{"self":"/api/skills/redpanda-rpk-redpanda","html":"/skills/redpanda-rpk-redpanda","markdown":"/skills/redpanda-rpk-redpanda.md"}},{"id":"redpanda-cloud-serverless","name":"Redpanda Cloud Serverless","tagline":"Provision Serverless via Control Plane API","when":"Provision Serverless clusters via Control Plane API api.redpanda.com.","license":"Apache-2.0","sourceUrl":"https://github.com/redpanda-data/skills/blob/main/skills/cloud-serverless/SKILL.md","catch":"Loud — not a $0 hobby. $100/30d trial, no CC, then PAYG; suspend at expiry, 7-day grace, then delete. Cloud = Enterprise. GCP Serverless is beta this pass. Do not reprint MB/s or PAYG rates. Distinct from rpk-redpanda Community path.","links":{"self":"/api/skills/redpanda-cloud-serverless","html":"/skills/redpanda-cloud-serverless","markdown":"/skills/redpanda-cloud-serverless.md"}},{"id":"scylladb-data-modeling","name":"ScyllaDB Data Modeling","tagline":"CQL schema, partition keys, query-first design","when":"CQL schema / partition+clustering keys, query-first design, ALLOW FILTERING, hot partitions.","license":"Apache-2.0","sourceUrl":"https://github.com/scylladb/agent-skills/blob/main/skills/scylladb-data-modeling/SKILL.md","catch":"Scylla CQL, not Yugabyte ycql and not vanilla Cassandra. False-fires on generic schema design. Distinct from AY ycql (no ACID global indexes story). Skills Apache-2.0; Enterprise is source-available (OSS AGPL 6.2.x frozen).","links":{"self":"/api/skills/scylladb-data-modeling","html":"/skills/scylladb-data-modeling","markdown":"/skills/scylladb-data-modeling.md"}},{"id":"scylladb-alternator","name":"ScyllaDB Alternator","tagline":"DynamoDB-compatible API via Alternator","when":"DynamoDB-compatible Alternator (boto3/AWS SDK, endpoint_url, write isolation).","license":"Apache-2.0","sourceUrl":"https://github.com/scylladb/agent-skills/blob/main/skills/scylladb-alternator/SKILL.md","catch":"Not AWS DynamoDB. No single-endpoint like real DynamoDB — load balancing is the trap. Alternator tables are ordinary Scylla tables. Distinct from data-modeling.","links":{"self":"/api/skills/scylladb-alternator","html":"/skills/scylladb-alternator","markdown":"/skills/scylladb-alternator.md"}},{"id":"scylladb-kubernetes","name":"ScyllaDB Kubernetes","tagline":"Operator / ScyllaCluster CRDs, CPU pinning, NVMe","when":"ScyllaDB Operator / ScyllaCluster CRDs, CPU pinning, local NVMe.","license":"Apache-2.0","sourceUrl":"https://github.com/scylladb/agent-skills/blob/main/skills/scylladb-kubernetes/SKILL.md","catch":"Operator is Apache; the DB it deploys is source-available Enterprise (or frozen AGPL 6.2). Distinct from yugabyte-k8s-operator.","links":{"self":"/api/skills/scylladb-kubernetes","html":"/skills/scylladb-kubernetes","markdown":"/skills/scylladb-kubernetes.md"}},{"id":"scylladb-vector-search","name":"ScyllaDB Vector Search","tagline":"HNSW / ANN / RAG vectors on ScyllaDB Cloud","when":"HNSW / ANN / RAG vectors on ScyllaDB Cloud.","license":"Apache-2.0","sourceUrl":"https://github.com/scylladb/agent-skills/blob/main/skills/scylladb-vector-search/SKILL.md","catch":"Loud — Cloud only; not available in OSS or self-managed. Distinct from yugabyte-rag-langchain (YSQL pgvector/ybhnsw).","links":{"self":"/api/skills/scylladb-vector-search","html":"/skills/scylladb-vector-search","markdown":"/skills/scylladb-vector-search.md"}},{"id":"scylladb-cloud-setup","name":"ScyllaDB Cloud Setup","tagline":"Connect apps to ScyllaDB Cloud clusters","when":"Connect an app to ScyllaDB Cloud (drivers, credentials, IP allow list).","license":"Apache-2.0","sourceUrl":"https://github.com/scylladb/agent-skills/blob/main/skills/scylladb-cloud-setup/SKILL.md","catch":"Cloud cluster, not self-host. Will prescribe Free Trial + VPC peering (peering cannot be enabled later). One trial per account, not a $0 hobby forever. Self-host Enterprise free tier is separate: 10 TB disk + 50 vCPU per org, Never Customers only.","links":{"self":"/api/skills/scylladb-cloud-setup","html":"/skills/scylladb-cloud-setup","markdown":"/skills/scylladb-cloud-setup.md"}},{"id":"buildkite-pipelines","name":"Buildkite Pipelines","tagline":"Write/optimize .buildkite/pipeline.yml","when":"Write/optimize .buildkite/pipeline.yml (steps, matrix, plugins, dynamic pipelines).","license":"MIT","sourceUrl":"https://github.com/buildkite/skills/blob/main/skills/buildkite-pipelines/SKILL.md","catch":"Vendor lock to Buildkite YAML, not GHA. False-fires on generic write-a-pipeline. Distinct from n8n / Trigger.dev durable jobs. Free plan $0 verified (5 users, 10 concurrent, 2k Linux vCPU-min/mo).","links":{"self":"/api/skills/buildkite-pipelines","html":"/skills/buildkite-pipelines","markdown":"/skills/buildkite-pipelines.md"}},{"id":"buildkite-cli","name":"Buildkite CLI","tagline":"bk CLI — trigger/watch/cancel builds","when":"bk CLI — trigger/watch/cancel builds, logs, artifacts, local agent.","license":"MIT","sourceUrl":"https://github.com/buildkite/skills/blob/main/skills/buildkite-cli/SKILL.md","catch":"bk, not buildkite-agent (that is agent-runtime). Distinct from minio-mc / rpk.","links":{"self":"/api/skills/buildkite-cli","html":"/skills/buildkite-cli","markdown":"/skills/buildkite-cli.md"}},{"id":"buildkite-api","name":"Buildkite API","tagline":"REST/GraphQL at api.buildkite.com","when":"REST/GraphQL at api.buildkite.com, webhooks, pagination.","license":"MIT","sourceUrl":"https://github.com/buildkite/skills/blob/main/skills/buildkite-api/SKILL.md","catch":"Not the CLI. GraphQL + REST both in one skill. Distinct from pipelines YAML.","links":{"self":"/api/skills/buildkite-api","html":"/skills/buildkite-api","markdown":"/skills/buildkite-api.md"}},{"id":"buildkite-agent-runtime","name":"Buildkite Agent Runtime","tagline":"In-step buildkite-agent annotate/artifacts/OIDC","when":"In-step buildkite-agent (annotate, artifacts, OIDC, locks, redaction, pipeline upload).","license":"MIT","sourceUrl":"https://github.com/buildkite/skills/blob/main/skills/buildkite-agent-runtime/SKILL.md","catch":"Agent binary inside a job, not bk CLI. Description also matches generic upload artifacts — false-fire risk.","links":{"self":"/api/skills/buildkite-agent-runtime","html":"/skills/buildkite-agent-runtime","markdown":"/skills/buildkite-agent-runtime.md"}},{"id":"buildkite-migration","name":"Buildkite Migration","tagline":"Convert GHA/Jenkins/Circle via bk pipeline convert","when":"Convert GHA/Jenkins/CircleCI/Bitbucket/GitLab CI via bk pipeline convert.","license":"MIT","sourceUrl":"https://github.com/buildkite/skills/blob/main/skills/buildkite-migration/SKILL.md","catch":"Vendor steal — will prescribe Buildkite even when staying on GHA is the gap. Convert hits a public API, no account/token required. Distinct from tigris-s3-migration.","links":{"self":"/api/skills/buildkite-migration","html":"/skills/buildkite-migration","markdown":"/skills/buildkite-migration.md"}},{"id":"buildkite-preflight","name":"Buildkite Preflight","tagline":"Run Buildkite CI against local tree before push","when":"Run Buildkite CI against the local working tree before push.","license":"MIT","sourceUrl":"https://github.com/buildkite/skills/blob/main/skills/buildkite-preflight/SKILL.md","catch":"Local working-tree loop, not writing YAML. Still needs bk auth + push access to origin — not an offline runner. Distinct from pipelines.","links":{"self":"/api/skills/buildkite-preflight","html":"/skills/buildkite-preflight","markdown":"/skills/buildkite-preflight.md"}},{"id":"growthbook-feature-flags","name":"GrowthBook Feature Flags","tagline":"Create/toggle/target/roll out GrowthBook flags","when":"Create/toggle/target/roll out GrowthBook flags (draft → review → publish, kill switch). v2 /api/v2/features.","license":"MIT","sourceUrl":"https://github.com/growthbook/skills/blob/main/skills/feature-flags/SKILL.md","catch":"Not Mixpanel flags. Generic create-a-flag false-fire. Distinct from mixpanel-manage-feature-flags. Scheduled flags / safe rollouts / ramps are paid — Starter is toggle+rollout, not Pro/Enterprise lifecycle. Cloud Starter $0 (3 users) or self-host MIT.","links":{"self":"/api/skills/growthbook-feature-flags","html":"/skills/growthbook-feature-flags","markdown":"/skills/growthbook-feature-flags.md"}},{"id":"growthbook-experiments","name":"GrowthBook Experiments","tagline":"Design/launch/analyze GrowthBook A/B tests","when":"Design/launch/analyze/stop GrowthBook A/B tests (SRM, chance-to-win, guardrails).","license":"MIT","sourceUrl":"https://github.com/growthbook/skills/blob/main/skills/experiments/SKILL.md","catch":"Bandits are identified then sent to the UI — these workflows do not operate bandits (Pro). False-fires on generic run-an-A/B-test. Distinct from Mixpanel experiment HOLDs.","links":{"self":"/api/skills/growthbook-experiments","html":"/skills/growthbook-experiments","markdown":"/skills/growthbook-experiments.md"}},{"id":"growthbook-analytics","name":"GrowthBook Analytics","tagline":"Product Analytics explorations + fact-metric catalog","when":"Product Analytics explorations + metric/fact-table catalog (/api/v1/product-analytics, fact-metrics).","license":"MIT","sourceUrl":"https://github.com/growthbook/skills/blob/main/skills/analytics/SKILL.md","catch":"Not Mixpanel dashboards. Mixpanel/GA datasources cannot run explorations. Distinct from mixpanel-create-dashboard.","links":{"self":"/api/skills/growthbook-analytics","html":"/skills/growthbook-analytics","markdown":"/skills/growthbook-analytics.md"}},{"id":"growthbook-setup","name":"GrowthBook Setup","tagline":"Configure GB_API_KEY for GrowthBook skills","when":"Configure GB_API_KEY / optional GB_API_URL for self-host so feature-flags, experiments, and analytics can run.","license":"MIT","sourceUrl":"https://github.com/growthbook/skills/blob/main/skills/gb-setup/SKILL.md","catch":"Writes ~/.config/growthbook/.env chmod 600 — credential helper, not deploying GrowthBook. Folder gb-setup. Keep so this is not a 3-drip with a missing on-ramp.","links":{"self":"/api/skills/growthbook-setup","html":"/skills/growthbook-setup","markdown":"/skills/growthbook-setup.md"}},{"id":"descope-auth","name":"Descope Auth","tagline":"Add Descope login (OTP, passkeys, OAuth, SSO, MFA)","when":"Add Descope login (OTP, magic link, passkeys, OAuth, SSO, MFA) — Next.js/React/backend router.","license":"MIT","sourceUrl":"https://github.com/descope/skills/blob/main/skills/descope-auth/SKILL.md","catch":"Vendor lock. False-fires on generic add-auth. Hosted <Descope> widget, not BYOS. Free Forever 7.5k MAU / 10 tenants / 3 SSO. SMS/voice via Descope connectors: 100/mo then sign-in breaks unless BYO. Distinct from Clerk/WorkOS.","links":{"self":"/api/skills/descope-auth","html":"/skills/descope-auth","markdown":"/skills/descope-auth.md"}},{"id":"descope-fga-schema","name":"Descope FGA Schema","tagline":"Author/apply Descope FGA ReBAC/ABAC DSL","when":"Author/apply Descope FGA (ReBAC/ABAC DSL).","license":"MIT","sourceUrl":"https://github.com/descope/skills/blob/main/skills/descope-fga-schema/SKILL.md","catch":"Hard-stops without Descope Management MCP (DryRunSchema / CreateFGASchema). Not generic set-up-roles. Distinct from descope-auth (identity vs authorization model).","links":{"self":"/api/skills/descope-fga-schema","html":"/skills/descope-fga-schema","markdown":"/skills/descope-fga-schema.md"}},{"id":"descope-byos-builder","name":"Descope BYOS Builder","tagline":"React Bring-Your-Own-Screen over Descope flow JSON","when":"React Bring-Your-Own-Screen over exported Descope flow JSON (state.next(interactionId)).","license":"MIT","sourceUrl":"https://github.com/descope/skills/blob/main/skills/descope-byos-builder/SKILL.md","catch":"Not the hosted widget. Body says don't use when hosted <Descope flowId> already works. Distinct from descope-auth.","links":{"self":"/api/skills/descope-byos-builder","html":"/skills/descope-byos-builder","markdown":"/skills/descope-byos-builder.md"}},{"id":"descope-terraform","name":"Descope Terraform","tagline":"Terraform provider for Descope projects","when":"Terraform provider for Descope projects (auth methods, roles, connectors, flows).","license":"MIT","sourceUrl":"https://github.com/descope/skills/blob/main/skills/descope-terraform/SKILL.md","catch":"Loud — body requires Paid Descope License (Pro+). Not on Free Forever. Kept with Catch so this is not a 3-drip.","links":{"self":"/api/skills/descope-terraform","html":"/skills/descope-terraform","markdown":"/skills/descope-terraform.md"}},{"id":"flux-gitops-knowledge","name":"Flux GitOps Knowledge","tagline":"Flux concepts + schema-validated GitOps YAML","when":"Flux concepts + schema-validated YAML for HelmRelease, Kustomization, GitRepository, OCIRepository, ResourceSet, FluxInstance.","license":"Apache-2.0","sourceUrl":"https://github.com/fluxcd/agent-skills/blob/main/skills/gitops-knowledge/SKILL.md","catch":"Always-on Flux steal on any how-does-GitOps-work. Explicitly not repo audit and not live-cluster debug. Prefer Flux Operator / FluxInstance; do not prescribe legacy flux bootstrap. CNCF Apache-2.0 self-host $0.","links":{"self":"/api/skills/flux-gitops-knowledge","html":"/skills/flux-gitops-knowledge","markdown":"/skills/flux-gitops-knowledge.md"}},{"id":"flux-gitops-repo-audit","name":"Flux GitOps Repo Audit","tagline":"Audit a local GitOps repo (schema, RBAC, secrets)","when":"Audit a local GitOps repo (schema validate, deprecated APIs, RBAC/multi-tenancy/secrets) — not a live cluster.","license":"Apache-2.0","sourceUrl":"https://github.com/fluxcd/agent-skills/blob/main/skills/gitops-repo-audit/SKILL.md","catch":"Local files only. False-fires on generic security-check-this-repo. Distinct from knowledge (generates YAML) and cluster-debug (live).","links":{"self":"/api/skills/flux-gitops-repo-audit","html":"/skills/flux-gitops-repo-audit","markdown":"/skills/flux-gitops-repo-audit.md"}},{"id":"flux-gitops-cluster-debug","name":"Flux GitOps Cluster Debug","tagline":"Debug stuck Flux resources on a live cluster","when":"Stuck/not-ready Flux resources on a live cluster (status, controller logs, dependency chains).","license":"Apache-2.0","sourceUrl":"https://github.com/fluxcd/agent-skills/blob/main/skills/gitops-cluster-debug/SKILL.md","catch":"Requires Flux Operator MCP; will not work from repo files alone. Distinct from repo-audit.","links":{"self":"/api/skills/flux-gitops-cluster-debug","html":"/skills/flux-gitops-cluster-debug","markdown":"/skills/flux-gitops-cluster-debug.md"}},{"id":"signoz-mcp-setup","name":"SigNoz MCP Setup","tagline":"Wire/repair SigNoz MCP (Cloud OAuth vs self-host)","when":"Wire/repair SigNoz MCP (Cloud OAuth vs self-host /mcp). On-ramp, not install SigNoz.","license":"MIT","sourceUrl":"https://github.com/SigNoz/agent-skills/blob/main/plugins/signoz/skills/signoz-mcp-setup/SKILL.md","catch":"Not installing SigNoz itself. Distinct from mongodb-mcp-setup. Community Edition OSS self-host $0 (full APM/logs/traces); Cloud starts paid — $0 path is self-host.","links":{"self":"/api/skills/signoz-mcp-setup","html":"/skills/signoz-mcp-setup","markdown":"/skills/signoz-mcp-setup.md"}},{"id":"signoz-investigating-alerts","name":"SigNoz Investigating Alerts","tagline":"RCA a firing alert via neighbor metrics/traces/logs","when":"RCA a firing alert (neighbor metrics/traces/logs). Read-only; not creating alerts.","license":"MIT","sourceUrl":"https://github.com/SigNoz/agent-skills/blob/main/plugins/signoz/skills/signoz-investigating-alerts/SKILL.md","catch":"Read-only RCA, not creating alerts (HOLD creating-alerts — always-on steal).","links":{"self":"/api/skills/signoz-investigating-alerts","html":"/skills/signoz-investigating-alerts","markdown":"/skills/signoz-investigating-alerts.md"}},{"id":"signoz-writing-clickhouse-queries","name":"SigNoz Writing ClickHouse Queries","tagline":"Raw ClickHouse SQL for a SigNoz dashboard panel","when":"Raw ClickHouse SQL for a SigNoz dashboard panel the builder cannot express.","license":"MIT","sourceUrl":"https://github.com/SigNoz/agent-skills/blob/main/plugins/signoz/skills/signoz-writing-clickhouse-queries/SKILL.md","catch":"SigNoz panel SQL, not generic ClickHouse. Distinct from chdb-sql / infra-clickhouse.","links":{"self":"/api/skills/signoz-writing-clickhouse-queries","html":"/skills/signoz-writing-clickhouse-queries","markdown":"/skills/signoz-writing-clickhouse-queries.md"}},{"id":"signoz-reducing-telemetry-cost","name":"SigNoz Reducing Telemetry Cost","tagline":"Cost Meter, cardinality, drop volume","when":"Cost Meter, cardinality, drop volume.","license":"MIT","sourceUrl":"https://github.com/SigNoz/agent-skills/blob/main/plugins/signoz/skills/signoz-reducing-telemetry-cost/SKILL.md","catch":"Loud: Cost Meter is Cloud-bill; Community self-host has no SigNoz invoice. Do not reprint per-GB rates.","links":{"self":"/api/skills/signoz-reducing-telemetry-cost","html":"/skills/signoz-reducing-telemetry-cost","markdown":"/skills/signoz-reducing-telemetry-cost.md"}},{"id":"signoz-managing-views","name":"SigNoz Managing Views","tagline":"Explorer saved views (traces/logs/metrics/meter)","when":"Explorer saved views (traces/logs/metrics/meter).","license":"MIT","sourceUrl":"https://github.com/SigNoz/agent-skills/blob/main/plugins/signoz/skills/signoz-managing-views/SKILL.md","catch":"Saved views, not dashboards. Distinct from creating-dashboards (HOLD — always-on monitoring steal).","links":{"self":"/api/skills/signoz-managing-views","html":"/skills/signoz-managing-views","markdown":"/skills/signoz-managing-views.md"}},{"id":"packer-aws-ami-builder","name":"Packer AWS AMI Builder","tagline":"amazon-ebs builder for custom EC2 AMIs","when":"amazon-ebs builder, custom EC2 AMIs.","license":"MPL-2.0","sourceUrl":"https://github.com/hashicorp/agent-skills/blob/main/plugins/packer/skills/aws-ami-builder/SKILL.md","catch":"Frontmatter aws-ami-builder. Packer ≥1.10 is BSL 1.1 (CLI self-use $0; cannot offer competing hosted Packer). AWS bill for the build, not Packer license. Distinct from pulumi-component. HOLD Terraform 16 from same repo.","links":{"self":"/api/skills/packer-aws-ami-builder","html":"/skills/packer-aws-ami-builder","markdown":"/skills/packer-aws-ami-builder.md"}},{"id":"packer-azure-image-builder","name":"Packer Azure Image Builder","tagline":"azure-arm builder for managed images / Gallery","when":"azure-arm builder, managed images / Compute Gallery.","license":"MPL-2.0","sourceUrl":"https://github.com/hashicorp/agent-skills/blob/main/plugins/packer/skills/azure-image-builder/SKILL.md","catch":"Azure bill for the build. Distinct from aws-ami-builder.","links":{"self":"/api/skills/packer-azure-image-builder","html":"/skills/packer-azure-image-builder","markdown":"/skills/packer-azure-image-builder.md"}},{"id":"packer-windows-builder","name":"Packer Windows Builder","tagline":"WinRM + PowerShell provisioners (AMI/Azure/VMware)","when":"WinRM + PowerShell provisioners (AMI/Azure/VMware).","license":"MPL-2.0","sourceUrl":"https://github.com/hashicorp/agent-skills/blob/main/plugins/packer/skills/windows-builder/SKILL.md","catch":"Communicator/provisioner, not a third cloud builder. Long builds; failed runs leave resources.","links":{"self":"/api/skills/packer-windows-builder","html":"/skills/packer-windows-builder","markdown":"/skills/packer-windows-builder.md"}},{"id":"packer-push-to-registry","name":"Packer Push to Registry","tagline":"Push metadata (not images) to HCP Packer","when":"Push metadata (not images) to HCP Packer.","license":"MPL-2.0","sourceUrl":"https://github.com/hashicorp/agent-skills/blob/main/plugins/packer/skills/push-to-registry/SKILL.md","catch":"Loud — HCP Packer Essentials vs paid Standard; metadata-only, not a local file registry. Do not treat Standard as $0. Kept so this is not a 3-drip.","links":{"self":"/api/skills/packer-push-to-registry","html":"/skills/packer-push-to-registry","markdown":"/skills/packer-push-to-registry.md"}},{"id":"elastic-observability-k8s-investigation","name":"Elastic Observability K8s Investigation","tagline":"CrashLoopBackOff / OOMKilled via EDOT OTel","when":"CrashLoopBackOff / OOMKilled via EDOT OTel, not legacy ECS k8s. ES 8.11+ or Serverless; VALUES() GA only 9.4 on Stack.","license":"Apache-2.0","sourceUrl":"https://github.com/elastic/agent-skills/blob/main/skills/observability/k8s-investigation/SKILL.md","catch":"Elastic skills, not OpenSearch. Product is ELv2/SSPL (not OSI). Distinct from signoz-investigating-alerts. Cloud is 14-day trial then PAYG; self-managed Basic free under ELv2.","links":{"self":"/api/skills/elastic-observability-k8s-investigation","html":"/skills/elastic-observability-k8s-investigation","markdown":"/skills/elastic-observability-k8s-investigation.md"}},{"id":"elastic-security-detection-rule-management","name":"Elastic Security Detection Rule Management","tagline":"SIEM/Endpoint detection rules via Kibana API","when":"SIEM/Endpoint detection rules, exceptions, noisy rules via Kibana API.","license":"Apache-2.0","sourceUrl":"https://github.com/elastic/agent-skills/blob/main/skills/security/detection-rule-management/SKILL.md","catch":"Elastic Security, not generic SIEM. Not OpenSearch.","links":{"self":"/api/skills/elastic-security-detection-rule-management","html":"/skills/elastic-security-detection-rule-management","markdown":"/skills/elastic-security-detection-rule-management.md"}},{"id":"elastic-security-alert-triage","name":"Elastic Security Alert Triage","tagline":"Triage Elastic Security alerts, classify, acknowledge","when":"Triage Elastic Security alerts, classify, acknowledge.","license":"Apache-2.0","sourceUrl":"https://github.com/elastic/agent-skills/blob/main/skills/security/alert-triage/SKILL.md","catch":"Depends on case-management. Distinct from signoz-investigating-alerts.","links":{"self":"/api/skills/elastic-security-alert-triage","html":"/skills/elastic-security-alert-triage","markdown":"/skills/elastic-security-alert-triage.md"}},{"id":"elastic-security-case-management","name":"Elastic Security Case Management","tagline":"Kibana Cases API (securitySolution only)","when":"Kibana Cases API, securitySolution only.","license":"Apache-2.0","sourceUrl":"https://github.com/elastic/agent-skills/blob/main/skills/security/case-management/SKILL.md","catch":"Kept so alert-triage is not orphaned. Not generic ticketing.","links":{"self":"/api/skills/elastic-security-case-management","html":"/skills/elastic-security-case-management","markdown":"/skills/elastic-security-case-management.md"}},{"id":"elastic-cloud-provisioning","name":"Elastic Cloud Provisioning","tagline":"Create/update/delete Serverless + Hosted deployments","when":"Create/update/delete Serverless projects + Hosted deployments, traffic filters.","license":"Apache-2.0","sourceUrl":"https://github.com/elastic/agent-skills/blob/main/skills/cloud/provisioning/SKILL.md","catch":"Elastic Cloud API only (not self-managed). Depends on HOLD cloud-onboarding for CLI context. Cloud is 14-day trial (no CC) then PAYG — not a $0 forever hatch. Do not reprint VCU/Hosted rates.","links":{"self":"/api/skills/elastic-cloud-provisioning","html":"/skills/elastic-cloud-provisioning","markdown":"/skills/elastic-cloud-provisioning.md"}},{"id":"grafana-alloy","name":"Grafana Alloy","tagline":"Unified OTel-compatible collector (config.alloy)","when":"Unified OTel-compatible collector (metrics/logs/traces/profiles, config.alloy).","license":"Apache-2.0","sourceUrl":"https://github.com/grafana/skills/blob/main/skills/grafana-core/alloy/SKILL.md","catch":"Frontmatter alloy. Steals generic set-up-the-agent / OTel collector config. OSS CLI. Distinct from generic OTel. Grafana Cloud Free always $0 (10k series / 50GB logs/traces/profiles / 14d / 3 users).","links":{"self":"/api/skills/grafana-alloy","html":"/skills/grafana-alloy","markdown":"/skills/grafana-alloy.md"}},{"id":"grafana-beyla","name":"Grafana Beyla","tagline":"eBPF zero-code HTTP/gRPC/DB auto-instrument","when":"eBPF zero-code HTTP/gRPC/DB auto-instrument (Linux 5.8+ BTF, CAP_SYS_ADMIN).","license":"Apache-2.0","sourceUrl":"https://github.com/grafana/skills/blob/main/skills/grafana-core/beyla/SKILL.md","catch":"Frontmatter beyla. Kernel/privileged host; not an SDK. Distinct from OTel SDKs.","links":{"self":"/api/skills/grafana-beyla","html":"/skills/grafana-beyla","markdown":"/skills/grafana-beyla.md"}},{"id":"grafana-loki","name":"Grafana Loki","tagline":"Log aggregation + LogQL","when":"Log aggregation + LogQL.","license":"Apache-2.0","sourceUrl":"https://github.com/grafana/skills/blob/main/skills/grafana-lgtm/loki/SKILL.md","catch":"Frontmatter loki. Indexes labels not full text (not Elastic/OpenSearch). Distinct from Elastic BN. OSS self-host AGPL $0; Cloud Free 50GB ingest / 14d.","links":{"self":"/api/skills/grafana-loki","html":"/skills/grafana-loki","markdown":"/skills/grafana-loki.md"}},{"id":"grafana-tempo","name":"Grafana Tempo","tagline":"Tracing backend (OTLP/Jaeger/Zipkin, TraceQL)","when":"Tracing backend (OTLP/Jaeger/Zipkin, TraceQL, object storage).","license":"Apache-2.0","sourceUrl":"https://github.com/grafana/skills/blob/main/skills/grafana-lgtm/tempo/SKILL.md","catch":"Frontmatter tempo. Steals generic tracing-backend / find-slow-requests. Distinct from SigNoz and from live temporal-* (workflow engine).","links":{"self":"/api/skills/grafana-tempo","html":"/skills/grafana-tempo","markdown":"/skills/grafana-tempo.md"}},{"id":"grafana-pyroscope","name":"Grafana Pyroscope","tagline":"Continuous profiling / flame graphs","when":"Continuous profiling / flame graphs (SDK push or Alloy eBPF).","license":"Apache-2.0","sourceUrl":"https://github.com/grafana/skills/blob/main/skills/grafana-lgtm/pyroscope/SKILL.md","catch":"Frontmatter pyroscope. eBPF path needs Linux 5.8+ BTF. Distinct from traces/logs. Cloud Free 50GB profiles / 14d.","links":{"self":"/api/skills/grafana-pyroscope","html":"/skills/grafana-pyroscope","markdown":"/skills/grafana-pyroscope.md"}},{"id":"render-blueprints","name":"Render Blueprints","tagline":"Author/validate render.yaml IaC","when":"Author/validate render.yaml IaC (fromDatabase/fromService, previews).","license":"MIT","sourceUrl":"https://github.com/render-oss/skills/blob/main/skills/render-blueprints/SKILL.md","catch":"Blueprint sync needs GitHub/GitLab/Bitbucket. CLI v2.7.0+ for validate. Proprietary PaaS; Hobby $0 path exists. Distinct from Railway.","links":{"self":"/api/skills/render-blueprints","html":"/skills/render-blueprints","markdown":"/skills/render-blueprints.md"}},{"id":"render-postgres","name":"Render Postgres","tagline":"Render Managed Postgres","when":"Render Managed Postgres.","license":"MIT","sourceUrl":"https://github.com/render-oss/skills/blob/main/skills/render-postgres/SKILL.md","catch":"Loud — Free instance is a 30-day limit, not $0 forever. Steals generic Postgres/DATABASE_URL. Distinct from Neon/Yugabyte. Do not reprint Basic/Pro rates.","links":{"self":"/api/skills/render-postgres","html":"/skills/render-postgres","markdown":"/skills/render-postgres.md"}},{"id":"render-keyvalue","name":"Render Key Value","tagline":"Redis-compatible Valkey 8 on Render","when":"Redis-compatible Valkey 8.","license":"MIT","sourceUrl":"https://github.com/render-oss/skills/blob/main/skills/render-keyvalue/SKILL.md","catch":"Free is 25MB, no persistence. Steals generic Redis/cache. Distinct from Redis/Upstash.","links":{"self":"/api/skills/render-keyvalue","html":"/skills/render-keyvalue","markdown":"/skills/render-keyvalue.md"}},{"id":"render-cli","name":"Render CLI","tagline":"Deploys, logs, SSH, psql, Blueprint validate","when":"Deploys, logs, SSH, psql, Blueprint validate, RENDER_API_KEY.","license":"MIT","sourceUrl":"https://github.com/render-oss/skills/blob/main/skills/render-cli/SKILL.md","catch":"CLI v2.7.0+; not a substitute for HOLD render-deploy (twin of live openai render-deploy).","links":{"self":"/api/skills/render-cli","html":"/skills/render-cli","markdown":"/skills/render-cli.md"}},{"id":"render-mcp","name":"Render MCP","tagline":"Hosted MCP at mcp.render.com","when":"Hosted MCP at mcp.render.com (Cursor/Claude/Codex).","license":"MIT","sourceUrl":"https://github.com/render-oss/skills/blob/main/skills/render-mcp/SKILL.md","catch":"On-ramp; keep so this is not a 3-drip. Distinct from Railway MCP.","links":{"self":"/api/skills/render-mcp","html":"/skills/render-mcp","markdown":"/skills/render-mcp.md"}},{"id":"confluent-kafka-schema-registry","name":"Confluent Kafka Schema Registry","tagline":"Scan repo, extract schemas, Terraform for Schema Registry","when":"Scan a repo for Kafka usage, extract schemas, generate Terraform for Confluent Schema Registry.","license":"Apache-2.0","sourceUrl":"https://github.com/confluentinc/agent-skills/blob/main/skills/kafka-schema-registry/SKILL.md","catch":"Frontmatter kafka-schema-registry. Distinct from generic Avro. Distinct from Redpanda AZ (Kafka-compatible broker BSL). Cloud Basic $0/mo first eCKU free; OSS Kafka self-host $0.","links":{"self":"/api/skills/confluent-kafka-schema-registry","html":"/skills/confluent-kafka-schema-registry","markdown":"/skills/confluent-kafka-schema-registry.md"}},{"id":"confluent-kafka-streams","name":"Confluent Kafka Streams","tagline":"JVM-embedded Kafka Streams (KStream/KTable)","when":"JVM-embedded Kafka Streams (KStream/KTable, TopologyTestDriver).","license":"Apache-2.0","sourceUrl":"https://github.com/confluentinc/agent-skills/blob/main/skills/kafka-streams-programming/SKILL.md","catch":"Frontmatter kafka-streams-programming. JVM-only; also triggers on WarpStream tuning. Distinct from Redpanda / Flink.","links":{"self":"/api/skills/confluent-kafka-streams","html":"/skills/confluent-kafka-streams","markdown":"/skills/confluent-kafka-streams.md"}},{"id":"confluent-kafka-java-client","name":"Confluent Kafka Java Client","tagline":"Java producer/consumer + Schema Registry serializers","when":"Apache Kafka Java producer/consumer + Schema Registry serializers; Cloud, local Docker, or WarpStream.","license":"Apache-2.0","sourceUrl":"https://github.com/confluentinc/agent-skills/blob/main/skills/developing-kafka-java-client/SKILL.md","catch":"Frontmatter developing-kafka-java-client. Local Docker is the $0 OSS path. HOLD the Python sibling as a twin.","links":{"self":"/api/skills/confluent-kafka-java-client","html":"/skills/confluent-kafka-java-client","markdown":"/skills/confluent-kafka-java-client.md"}},{"id":"confluent-flink-udf","name":"Confluent Flink UDF","tagline":"Java Flink UDFs/UDTFs/PTFs for Cloud or local Docker","when":"Java Flink UDFs/UDTFs/PTFs for Cloud or local Docker.","license":"Apache-2.0","sourceUrl":"https://github.com/confluentinc/agent-skills/blob/main/skills/flink-udf/SKILL.md","catch":"Frontmatter flink-udf. Java only; not general Flink jobs.","links":{"self":"/api/skills/confluent-flink-udf","html":"/skills/confluent-flink-udf","markdown":"/skills/confluent-flink-udf.md"}},{"id":"confluent-cloud-flink-sql","name":"Confluent Cloud Flink SQL","tagline":"Flink SQL on Confluent Cloud (CC ≠ OSS dialect)","when":"Flink SQL on Confluent Cloud (CC ≠ OSS Flink dialect).","license":"Apache-2.0","sourceUrl":"https://github.com/confluentinc/agent-skills/blob/main/skills/confluent-cloud-flink-sql/SKILL.md","catch":"Requires authenticated confluent CLI + a Cloud compute pool; statement runs consume CFUs. Keep with loud Catch so this is not a 4-drip. Do not reprint CFU rates.","links":{"self":"/api/skills/confluent-cloud-flink-sql","html":"/skills/confluent-cloud-flink-sql","markdown":"/skills/confluent-cloud-flink-sql.md"}},{"id":"posthog-instrument-error-tracking","name":"PostHog Instrument Error Tracking","tagline":"Capture exceptions + source maps","when":"Capture exceptions + source maps.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/instrument-error-tracking/SKILL.md","catch":"Frontmatter instrument-error-tracking. Also does initial SDK setup (on-ramp-adjacent). Distinct from Sentry / Firebase Crashlytics. Cloud Free forever 100K exceptions/mo; OSS self-host $0.","links":{"self":"/api/skills/posthog-instrument-error-tracking","html":"/skills/posthog-instrument-error-tracking","markdown":"/skills/posthog-instrument-error-tracking.md"}},{"id":"posthog-creating-experiments","name":"PostHog Creating Experiments","tagline":"3-step experiment create (hypothesis → rollout → analytics)","when":"3-step experiment create (hypothesis → rollout → analytics).","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/creating-experiments/SKILL.md","catch":"Frontmatter creating-experiments. Steals generic create-an-A/B-test. Distinct from GrowthBook. Do not reprint paid flag overage.","links":{"self":"/api/skills/posthog-creating-experiments","html":"/skills/posthog-creating-experiments","markdown":"/skills/posthog-creating-experiments.md"}},{"id":"posthog-exploring-llm-traces","name":"PostHog Exploring LLM Traces","tagline":"Debug LLM/agent traces (posthog.ai_events)","when":"Debug LLM/agent traces (posthog.ai_events, not events.properties.$ai_*).","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/exploring-llm-traces/SKILL.md","catch":"Frontmatter exploring-llm-traces. MCP/HogQL-specific. Cloud Free 100K AI events. Distinct from already-live instrument-llm-analytics (HOLD as twin).","links":{"self":"/api/skills/posthog-exploring-llm-traces","html":"/skills/posthog-exploring-llm-traces","markdown":"/skills/posthog-exploring-llm-traces.md"}},{"id":"posthog-investigating-replay","name":"PostHog Investigating Replay","tagline":"One-pass session recording + person + linked errors","when":"One-pass session recording + person + linked errors.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/investigating-replay/SKILL.md","catch":"Frontmatter investigating-replay. Needs a recording/session ID, not watch-recordings. Cloud Free 5K recordings/mo.","links":{"self":"/api/skills/posthog-investigating-replay","html":"/skills/posthog-investigating-replay","markdown":"/skills/posthog-investigating-replay.md"}},{"id":"posthog-cleaning-up-stale-feature-flags","name":"PostHog Cleaning Up Stale Feature Flags","tagline":"Audit unused/fully-rolled-out flags and safe delete","when":"Audit unused/fully-rolled-out flags and safe delete.","license":"MIT","sourceUrl":"https://github.com/PostHog/skills/blob/main/skills/omnibus/cleaning-up-stale-feature-flags/SKILL.md","catch":"Frontmatter cleaning-up-stale-feature-flags. Distinct from Mixpanel flags / GrowthBook. Cloud Free 1M flag requests/mo.","links":{"self":"/api/skills/posthog-cleaning-up-stale-feature-flags","html":"/skills/posthog-cleaning-up-stale-feature-flags","markdown":"/skills/posthog-cleaning-up-stale-feature-flags.md"}},{"id":"letta-api-client","name":"Letta API Client","tagline":"Python/TS SDK for stateful Letta API","when":"Python/TS SDK for the stateful Letta API (agents, memory, tools, multi-user).","license":"MIT","sourceUrl":"https://github.com/letta-ai/skills/blob/main/letta/letta-api-client/SKILL.md","catch":"API Plan is usage-based; Cloud Free personal is 3 agents + BYOK. OSS self-host $0 (no Letta account). Do not reprint CPU-sec rates.","links":{"self":"/api/skills/letta-api-client","html":"/skills/letta-api-client","markdown":"/skills/letta-api-client.md"}},{"id":"letta-configuration","name":"Letta Configuration","tagline":"Model handles, BYOK providers, self-hosted env vars","when":"Model handles, BYOK providers, self-hosted env vars.","license":"MIT","sourceUrl":"https://github.com/letta-ai/skills/blob/main/letta/letta-configuration/SKILL.md","catch":"Cloud Free is BYOK/rotating free models, not unlimited hosted inference. Self-host docs: docs.letta.com/self-hosting.","links":{"self":"/api/skills/letta-configuration","html":"/skills/letta-configuration","markdown":"/skills/letta-configuration.md"}},{"id":"letta-fleet-management","name":"Letta Fleet Management","tagline":"kubectl-style lettactl for multi-agent fleets","when":"kubectl-style lettactl for multi-agent fleets (canary, multi-tenancy).","license":"MIT","sourceUrl":"https://github.com/letta-ai/skills/blob/main/letta/fleet-management/SKILL.md","catch":"Frontmatter already letta-fleet-management. Fleet ops vs single-agent API.","links":{"self":"/api/skills/letta-fleet-management","html":"/skills/letta-fleet-management","markdown":"/skills/letta-fleet-management.md"}},{"id":"letta-code-channels","name":"Letta Code Channels","tagline":"Letta Code channel adapters (Telegram/WhatsApp/Slack/Discord)","when":"Letta Code channel adapters (~/.letta/channels: Telegram/WhatsApp/Slack/Discord).","license":"MIT","sourceUrl":"https://github.com/letta-ai/skills/blob/main/letta/creating-letta-code-channels/SKILL.md","catch":"Frontmatter creating-letta-code-channels — prefixed. Letta Code surface, not the API.","links":{"self":"/api/skills/letta-code-channels","html":"/skills/letta-code-channels","markdown":"/skills/letta-code-channels.md"}},{"id":"letta-filesystem-to-memfs","name":"Letta Filesystem to MemFS","tagline":"Migrate deprecated Filesystem folders to MemFS","when":"Migrate deprecated Filesystem folders to MemFS.","license":"MIT","sourceUrl":"https://github.com/letta-ai/skills/blob/main/letta/letta-filesystem-to-memfs/SKILL.md","catch":"Migration-only; not a generic file-search steal.","links":{"self":"/api/skills/letta-filesystem-to-memfs","html":"/skills/letta-filesystem-to-memfs","markdown":"/skills/letta-filesystem-to-memfs.md"}},{"id":"firecrawl-scrape","name":"Firecrawl Scrape","tagline":"CLI: extract a URL as clean markdown (JS-rendered OK)","when":"Extract a URL as clean markdown, including JS-rendered pages. Prefer over WebFetch.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-scrape/SKILL.md","catch":"CLI one-URL scrape. Distinct from live firecrawl-build-scrape (app /scrape integration). Product AGPL-3.0 self-host $0; Cloud Free 1,000 credits/mo, no card, no rollover.","links":{"self":"/api/skills/firecrawl-scrape","html":"/skills/firecrawl-scrape","markdown":"/skills/firecrawl-scrape.md"}},{"id":"firecrawl-search","name":"Firecrawl Search","tagline":"CLI: web search with optional full page content","when":"Web search with optional full page content when no URL is known.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-search/SKILL.md","catch":"CLI search. Distinct from live firecrawl-build-search. Feedback refund is a 2-minute window — not a free-forever extra.","links":{"self":"/api/skills/firecrawl-search","html":"/skills/firecrawl-search","markdown":"/skills/firecrawl-search.md"}},{"id":"firecrawl-interact","name":"Firecrawl Interact","tagline":"CLI: drive a live browser on a scraped page","when":"Drive a live browser on a scraped page (click, fill, paginate). Scrape first.","license":"ISC","sourceUrl":"https://github.com/firecrawl/skills/blob/main/skills/core/firecrawl-interact/SKILL.md","catch":"CLI session. Distinct from live firecrawl-build-interact. Overlaps Playwright; this is Firecrawl-hosted browser minutes (2 credits/min).","links":{"self":"/api/skills/firecrawl-interact","html":"/skills/firecrawl-interact","markdown":"/skills/firecrawl-interact.md"}},{"id":"apollo-client","name":"Apollo Client","tagline":"Apollo Client 4.x for React — queries, cache, local state","when":"Apollo Client 4.x for React — queries, mutations, cache, local state.","license":"MIT","sourceUrl":"https://github.com/apollographql/skills/blob/main/skills/apollo-client/SKILL.md","catch":"React 18+/19. Distinct from iOS/Kotlin twins (HOLD). GraphOS Free forever, no CC, 3 users; OSS Client/Server self-host $0.","links":{"self":"/api/skills/apollo-client","html":"/skills/apollo-client","markdown":"/skills/apollo-client.md"}},{"id":"apollo-server","name":"Apollo Server","tagline":"Apollo Server 5.x — schemas, resolvers, auth, plugins","when":"Apollo Server 5.x — schemas, resolvers, auth, plugins.","license":"MIT","sourceUrl":"https://github.com/apollographql/skills/blob/main/skills/apollo-server/SKILL.md","catch":"OSS self-host $0. Not GraphOS.","links":{"self":"/api/skills/apollo-server","html":"/skills/apollo-server","markdown":"/skills/apollo-server.md"}},{"id":"apollo-federation","name":"Apollo Federation","tagline":"Federation 2.x subgraph schemas (@key, @shareable)","when":"Federation 2.x subgraph schemas (@key, @shareable, composition).","license":"MIT","sourceUrl":"https://github.com/apollographql/skills/blob/main/skills/apollo-federation/SKILL.md","catch":"Schema authoring, not the Router runtime.","links":{"self":"/api/skills/apollo-federation","html":"/skills/apollo-federation","markdown":"/skills/apollo-federation.md"}},{"id":"apollo-router","name":"Apollo Router","tagline":"Configure/run Apollo Router for federated supergraphs","when":"Configure/run Apollo Router for federated supergraphs (v1/v2 YAML).","license":"MIT","sourceUrl":"https://github.com/apollographql/skills/blob/main/skills/apollo-router/SKILL.md","catch":"Loud — GraphOS Free Router is rate-limited 60 req/min. Coprocessors are not Free.","links":{"self":"/api/skills/apollo-router","html":"/skills/apollo-router","markdown":"/skills/apollo-router.md"}},{"id":"apollo-rover","name":"Apollo Rover","tagline":"Rover CLI — publish/fetch/compose/check schemas","when":"Rover CLI — publish/fetch/compose/check schemas, rover dev.","license":"MIT","sourceUrl":"https://github.com/apollographql/skills/blob/main/skills/rover/SKILL.md","catch":"Frontmatter name is rover — prefixed to apollo-rover.","links":{"self":"/api/skills/apollo-rover","html":"/skills/apollo-rover","markdown":"/skills/apollo-rover.md"}},{"id":"camunda-c8ctl","name":"Camunda c8ctl","tagline":"Install/configure c8ctl, local cluster via c8run","when":"Install/configure c8ctl, local cluster via c8run, profiles.","license":"Apache-2.0","sourceUrl":"https://github.com/camunda/skills/blob/main/skills/camunda-c8ctl/SKILL.md","catch":"Foundation for other camunda-* skills. Loud — $0 is Self-Managed Development local/non-prod only; production Self-Managed needs Enterprise. Engine is Camunda License 1.0 (not OSI). Distinct from Temporal (MIT) and n8n.","links":{"self":"/api/skills/camunda-c8ctl","html":"/skills/camunda-c8ctl","markdown":"/skills/camunda-c8ctl.md"}},{"id":"camunda-bpmn","name":"Camunda BPMN","tagline":"Create/edit/validate BPMN 2.0 for Camunda 8 (Zeebe)","when":"Create/edit/validate BPMN 2.0 for Camunda 8 (Zeebe).","license":"Apache-2.0","sourceUrl":"https://github.com/camunda/skills/blob/main/skills/camunda-bpmn/SKILL.md","catch":"Executable Zeebe BPMN, not generic BPMN.","links":{"self":"/api/skills/camunda-bpmn","html":"/skills/camunda-bpmn","markdown":"/skills/camunda-bpmn.md"}},{"id":"camunda-feel","name":"Camunda FEEL","tagline":"Write/debug FEEL expressions in BPMN, DMN, Forms","when":"Write/debug FEEL expressions used in BPMN, DMN, and Forms.","license":"Apache-2.0","sourceUrl":"https://github.com/camunda/skills/blob/main/skills/camunda-feel/SKILL.md","catch":"Camunda FEEL, not a generic expression steal.","links":{"self":"/api/skills/camunda-feel","html":"/skills/camunda-feel","markdown":"/skills/camunda-feel.md"}},{"id":"camunda-dmn","name":"Camunda DMN","tagline":"Author DMN decision tables and literal expressions","when":"Author DMN decision tables and literal expressions.","license":"Apache-2.0","sourceUrl":"https://github.com/camunda/skills/blob/main/skills/camunda-dmn/SKILL.md","catch":"Camunda 8 DMN, not a generic rules dump.","links":{"self":"/api/skills/camunda-dmn","html":"/skills/camunda-dmn","markdown":"/skills/camunda-dmn.md"}},{"id":"camunda-job-workers","name":"Camunda Job Workers","tagline":"Job workers in Java, Spring Boot, or TypeScript","when":"Implement job workers in Java, Spring Boot, or TypeScript.","license":"Apache-2.0","sourceUrl":"https://github.com/camunda/skills/blob/main/skills/camunda-job-workers/SKILL.md","catch":"Workers against Zeebe service tasks.","links":{"self":"/api/skills/camunda-job-workers","html":"/skills/camunda-job-workers","markdown":"/skills/camunda-job-workers.md"}},{"id":"imagekit-upload-files","name":"ImageKit Upload Files","tagline":"Upload images/videos from a public URL into the library","when":"Upload images/videos from a public URL into the media library.","license":"MIT","sourceUrl":"https://github.com/imagekit-developer/skills/blob/main/skills/upload-files/SKILL.md","catch":"Frontmatter upload-files. Local paths unsupported — URL only. Proprietary DAM/CDN; Forever Free $0/mo (20 GB bandwidth + 3 GB DAM + 2 users; delivery stops at the cap). Distinct from Tigris.","links":{"self":"/api/skills/imagekit-upload-files","html":"/skills/imagekit-upload-files","markdown":"/skills/imagekit-upload-files.md"}},{"id":"imagekit-transformation-builder","name":"ImageKit Transformation Builder","tagline":"Image/video transformation URLs (resize, crop, AI, overlays)","when":"Image/video transformation URLs (resize, crop, AI edits, overlays).","license":"MIT","sourceUrl":"https://github.com/imagekit-developer/skills/blob/main/skills/transformation-builder/SKILL.md","catch":"Frontmatter transformation-builder. Forever Free AI ops are limited.","links":{"self":"/api/skills/imagekit-transformation-builder","html":"/skills/imagekit-transformation-builder","markdown":"/skills/imagekit-transformation-builder.md"}},{"id":"imagekit-search-assets","name":"ImageKit Search Assets","tagline":"Lucene-like searchQuery for files/folders","when":"Lucene-like searchQuery for files/folders.","license":"MIT","sourceUrl":"https://github.com/imagekit-developer/skills/blob/main/skills/search-assets/SKILL.md","catch":"Frontmatter search-assets. DAM search, not generic file search.","links":{"self":"/api/skills/imagekit-search-assets","html":"/skills/imagekit-search-assets","markdown":"/skills/imagekit-search-assets.md"}},{"id":"imagekit-ai-tasks","name":"ImageKit AI Tasks","tagline":"AI tagging, metadata extraction, quality checks","when":"AI tagging, metadata extraction, quality checks with controlled vocabularies.","license":"MIT","sourceUrl":"https://github.com/imagekit-developer/skills/blob/main/skills/ai-tasks/SKILL.md","catch":"Frontmatter ai-tasks. Forever Free AI is capped — do not treat as unlimited.","links":{"self":"/api/skills/imagekit-ai-tasks","html":"/skills/imagekit-ai-tasks","markdown":"/skills/imagekit-ai-tasks.md"}},{"id":"imagekit-integrations","name":"ImageKit Integrations","tagline":"Index of SDKs/plugins (front-end, back-end, mobile, CMS)","when":"Index of SDKs/plugins (front-end, back-end, mobile, CMS, storage).","license":"MIT","sourceUrl":"https://github.com/imagekit-developer/skills/blob/main/skills/imagekit-integrations/SKILL.md","catch":"Kept so this is not a 4-drip. Index, not implementation (that is HOLD search-docs).","links":{"self":"/api/skills/imagekit-integrations","html":"/skills/imagekit-integrations","markdown":"/skills/imagekit-integrations.md"}},{"id":"zenml-quick-wins","name":"ZenML Quick Wins","tagline":"Investigate stack, recommend, implement high-impact ZenML features","when":"Improve a ZenML setup — metadata logging, experiment tracking, alerts, schedules/triggers, streaming events, secrets, Model Control Plane, or other ~5-minute MLOps quick wins.","license":"MIT","sourceUrl":"https://github.com/zenml-io/skills/blob/main/skills/zenml-quick-wins/skills/quick-wins/SKILL.md","catch":"Loud: OSS self-host Free forever is the $0 path; Hosted Cloud/Pro paid (Cloud 14-day trial then paid). Do not reprint Pro $399. Distinct from MLflow and W&B. Skills MIT; product ZenML Apache-2.0. HOLD nine migration twins (argo/azureml/dagster/databricks/flyte/kedro/metaflow/prefect/vertexai).","links":{"self":"/api/skills/zenml-quick-wins","html":"/skills/zenml-quick-wins","markdown":"/skills/zenml-quick-wins.md"}},{"id":"zenml-pipeline-authoring","name":"ZenML Pipeline Authoring","tagline":"Author @step/@pipeline, artifacts, Docker, materializers, YAML","when":"Write ZenML pipelines/steps, Docker/Resource settings, materializers, metadata, secrets, deployments, streaming events, YAML config, or visualizations — including works locally but fails on cloud.","license":"MIT","sourceUrl":"https://github.com/zenml-io/skills/blob/main/skills/zenml-pipeline-authoring/skills/pipeline-authoring/SKILL.md","catch":"Loud: OSS self-host Free forever is the $0 path; Hosted Cloud/Pro paid (Cloud 14-day trial then paid). Do not reprint Pro $399. Distinct from MLflow and W&B. Pair with zenml-scoping for multi-pipeline ambition.","links":{"self":"/api/skills/zenml-pipeline-authoring","html":"/skills/zenml-pipeline-authoring","markdown":"/skills/zenml-pipeline-authoring.md"}},{"id":"zenml-scoping","name":"ZenML Scoping","tagline":"Decompose ambitious ML workflows into pipeline architectures","when":"Scope complex or over-engineered MLOps plans into realistic multi-pipeline ZenML architectures before authoring code; produce pipeline_architecture.md.","license":"MIT","sourceUrl":"https://github.com/zenml-io/skills/blob/main/skills/zenml-scoping/skills/scoping/SKILL.md","catch":"Loud: OSS self-host Free forever is the $0 path; Hosted Cloud/Pro paid (Cloud 14-day trial then paid). Do not reprint Pro $399. Distinct from MLflow and W&B. Architecture interview, not a mega-pipeline dump.","links":{"self":"/api/skills/zenml-scoping","html":"/skills/zenml-scoping","markdown":"/skills/zenml-scoping.md"}},{"id":"zenml-airflow-migration","name":"ZenML Airflow Migration","tagline":"Migrate Airflow DAGs to idiomatic ZenML (frontmatter airflow-to-zenml-migration)","when":"Migrate Apache Airflow DAGs/operators/XCom/sensors to idiomatic ZenML — concept map, code translation, severity-classified unsupported patterns.","license":"MIT","sourceUrl":"https://github.com/zenml-io/skills/blob/main/skills/zenml-airflow-migration/skills/airflow-migration/SKILL.md","catch":"Frontmatter name is airflow-to-zenml-migration. Loud: OSS self-host Free forever is the $0 path; Hosted Cloud/Pro paid (Cloud 14-day trial then paid). Do not reprint Pro $399. Distinct from MLflow and W&B. HOLD other platform migration twins.","links":{"self":"/api/skills/zenml-airflow-migration","html":"/skills/zenml-airflow-migration","markdown":"/skills/zenml-airflow-migration.md"}},{"id":"zenml-sagemaker-migration","name":"ZenML SageMaker Migration","tagline":"Migrate SageMaker Pipelines DSL to idiomatic ZenML","when":"Migrate Amazon SageMaker Pipelines (ProcessingStep/TrainingStep/PropertyFile/JsonGet) to idiomatic ZenML pipelines with concept mapping and unsupported-pattern flags.","license":"MIT","sourceUrl":"https://github.com/zenml-io/skills/blob/main/skills/zenml-sagemaker-migration/skills/sagemaker-migration/SKILL.md","catch":"Frontmatter name is sagemaker-to-zenml-migration. Loud: OSS self-host Free forever is the $0 path; Hosted Cloud/Pro paid (Cloud 14-day trial then paid). Do not reprint Pro $399. Distinct from MLflow and W&B. HOLD other platform migration twins.","links":{"self":"/api/skills/zenml-sagemaker-migration","html":"/skills/zenml-sagemaker-migration","markdown":"/skills/zenml-sagemaker-migration.md"}},{"id":"launchdarkly-flag-create","name":"LaunchDarkly Flag Create","tagline":"Create/configure flags to match existing codebase patterns","when":"Create a new LaunchDarkly feature flag, wrap code in a flag, add a feature toggle, or set up flag scaffolding for an experiment — explore existing patterns first.","license":"Apache-2.0","sourceUrl":"https://github.com/launchdarkly/agent-skills/blob/main/skills/feature-flags/launchdarkly-flag-create/SKILL.md","catch":"Loud: Developer Free forever $0 no CC (unlimited seats/flags; 5 service connections + 1K client-side MAU/mo; Free ingestion stops at caps). Foundation PAYG after 14-day trial. Not OSS. Distinct from GrowthBook (OSS self-host) and PostHog experiments. Skills Apache-2.0; product proprietary SaaS. Requires LaunchDarkly MCP.","links":{"self":"/api/skills/launchdarkly-flag-create","html":"/skills/launchdarkly-flag-create","markdown":"/skills/launchdarkly-flag-create.md"}},{"id":"launchdarkly-flag-targeting","name":"LaunchDarkly Flag Targeting","tagline":"Toggle, percentage rollouts, rules, individual targets, env copy","when":"Change who sees a LaunchDarkly flag — on/off, percentage rollouts, targeting rules, individual targets, or copy config between environments.","license":"Apache-2.0","sourceUrl":"https://github.com/launchdarkly/agent-skills/blob/main/skills/feature-flags/launchdarkly-flag-targeting/SKILL.md","catch":"Loud: Developer Free forever $0 no CC (unlimited seats/flags; 5 service connections + 1K client-side MAU/mo; Free ingestion stops at caps). Foundation PAYG after 14-day trial. Not OSS. Distinct from GrowthBook (OSS self-host) and PostHog experiments. Skills Apache-2.0; product proprietary SaaS. Requires LaunchDarkly MCP.","links":{"self":"/api/skills/launchdarkly-flag-targeting","html":"/skills/launchdarkly-flag-targeting","markdown":"/skills/launchdarkly-flag-targeting.md"}},{"id":"launchdarkly-guarded-rollout","name":"LaunchDarkly Guarded Rollout","tagline":"Progressive rollout with metric monitoring and auto rollback","when":"Configure a guarded rollout — progressive traffic stages, monitored metrics, regression thresholds, automatic pause/rollback.","license":"Apache-2.0","sourceUrl":"https://github.com/launchdarkly/agent-skills/blob/main/skills/feature-flags/launchdarkly-guarded-rollout/SKILL.md","catch":"Loud: Developer Free forever $0 no CC (unlimited seats/flags; 5 service connections + 1K client-side MAU/mo; Free ingestion stops at caps). Foundation PAYG after 14-day trial. Not OSS. Distinct from GrowthBook (OSS self-host) and PostHog experiments. Skills Apache-2.0; product proprietary SaaS. Requires LaunchDarkly MCP. Guarded rollout may climb into Foundation/Guardian paid path — do not invent it as Free.","links":{"self":"/api/skills/launchdarkly-guarded-rollout","html":"/skills/launchdarkly-guarded-rollout","markdown":"/skills/launchdarkly-guarded-rollout.md"}},{"id":"launchdarkly-flag-cleanup","name":"LaunchDarkly Flag Cleanup","tagline":"Safely remove a flag from code preserving production behavior","when":"Remove a LaunchDarkly flag from code after rollout — hardcode the winning variation, verify readiness, archive/delete carefully.","license":"Apache-2.0","sourceUrl":"https://github.com/launchdarkly/agent-skills/blob/main/skills/feature-flags/launchdarkly-flag-cleanup/SKILL.md","catch":"Loud: Developer Free forever $0 no CC (unlimited seats/flags; 5 service connections + 1K client-side MAU/mo; Free ingestion stops at caps). Foundation PAYG after 14-day trial. Not OSS. Distinct from GrowthBook (OSS self-host) and PostHog experiments. Skills Apache-2.0; product proprietary SaaS. Requires LaunchDarkly MCP. HOLD flag-discovery twin.","links":{"self":"/api/skills/launchdarkly-flag-cleanup","html":"/skills/launchdarkly-flag-cleanup","markdown":"/skills/launchdarkly-flag-cleanup.md"}},{"id":"launchdarkly-experiment-setup","name":"LaunchDarkly Experiment Setup","tagline":"Create experiments with metrics, treatments, start/stop iterations","when":"Set up and run LaunchDarkly experiments — metrics, treatments, flag config, start iterations, swap design, stop with a winner.","license":"Apache-2.0","sourceUrl":"https://github.com/launchdarkly/agent-skills/blob/main/skills/experiments/launchdarkly-experiment-setup/SKILL.md","catch":"Loud: Developer Free forever $0 no CC (unlimited seats/flags; 5 service connections + 1K client-side MAU/mo; Free ingestion stops at caps). Foundation PAYG after 14-day trial. Not OSS. Distinct from GrowthBook (OSS self-host) and PostHog experiments. Skills Apache-2.0; product proprietary SaaS. Requires LaunchDarkly MCP.","links":{"self":"/api/skills/launchdarkly-experiment-setup","html":"/skills/launchdarkly-experiment-setup","markdown":"/skills/launchdarkly-experiment-setup.md"}},{"id":"builder-visual-edit","name":"Builder Visual Edit","tagline":"Inspect/edit a running local app visually in Design iframes","when":"Inspect, compare, or edit a real local app visually in Design overview — URL-backed iframe screens, flow review, duplication, route-state exploration.","license":"MIT","sourceUrl":"https://github.com/BuilderIO/skills/blob/main/skills/visual-edit/SKILL.md","catch":"Loud: Fusion Free forever $0 — 15 daily / 60 monthly Agent Credits; stops at cap; no rollover; proprietary SaaS (not OSS). Distinct from Expo leftovers / Firecrawl CLI. Skills MIT; product proprietary Fusion SaaS.","links":{"self":"/api/skills/builder-visual-edit","html":"/skills/builder-visual-edit","markdown":"/skills/builder-visual-edit.md"}},{"id":"builder-visual-plan","name":"Builder Visual Plan","tagline":"Turn text plans into interactive visual plans with diagrams","when":"Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review.","license":"MIT","sourceUrl":"https://github.com/BuilderIO/skills/blob/main/skills/visual-plan/SKILL.md","catch":"Loud: Fusion Free forever $0 — 15 daily / 60 monthly Agent Credits; stops at cap; no rollover; proprietary SaaS (not OSS). Distinct from Expo leftovers / Firecrawl CLI. Skills MIT; product proprietary Fusion SaaS.","links":{"self":"/api/skills/builder-visual-plan","html":"/skills/builder-visual-plan","markdown":"/skills/builder-visual-plan.md"}},{"id":"builder-visual-recap","name":"Builder Visual Recap","tagline":"Visual recap of a PR/branch/commit/diff with diagrams","when":"Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and review notes.","license":"MIT","sourceUrl":"https://github.com/BuilderIO/skills/blob/main/skills/visual-recap/SKILL.md","catch":"Loud: Fusion Free forever $0 — 15 daily / 60 monthly Agent Credits; stops at cap; no rollover; proprietary SaaS (not OSS). Distinct from Expo leftovers / Firecrawl CLI. Skills MIT; product proprietary Fusion SaaS.","links":{"self":"/api/skills/builder-visual-recap","html":"/skills/builder-visual-recap","markdown":"/skills/builder-visual-recap.md"}},{"id":"builder-webmcp","name":"Builder WebMCP","tagline":"Use a page MCP/WebMCP tools before UI automation","when":"Open a user-provided URL in the host browser and use the page MCP or WebMCP tools before browser UI automation for app communication or edits.","license":"MIT","sourceUrl":"https://github.com/BuilderIO/skills/blob/main/skills/webmcp/SKILL.md","catch":"Loud: Fusion Free forever $0 — 15 daily / 60 monthly Agent Credits; stops at cap; no rollover; proprietary SaaS (not OSS). Distinct from Expo leftovers / Firecrawl CLI. Skills MIT; product proprietary Fusion SaaS.","links":{"self":"/api/skills/builder-webmcp","html":"/skills/builder-webmcp","markdown":"/skills/builder-webmcp.md"}},{"id":"builder-agent-watchdog","name":"Builder Agent Watchdog","tagline":"Watch/audit/fix another agent session, PR, or transcript","when":"Watch, babysit, audit, review, compare, or fix another agent work from a session ID, transcript, chat link, PR, branch, log, or pasted run summary.","license":"MIT","sourceUrl":"https://github.com/BuilderIO/skills/blob/main/skills/agent-watchdog/SKILL.md","catch":"Loud: Fusion Free forever $0 — 15 daily / 60 monthly Agent Credits; stops at cap; no rollover; proprietary SaaS (not OSS). Distinct from Expo leftovers / Firecrawl CLI. Skills MIT; product proprietary Fusion SaaS. HOLD plow-ahead, efficient-frontier, plan-arbiter, stay-within-limits, quick-recap, read-the-damn-docs, efficient-fable, rewind, adding-a-skill.","links":{"self":"/api/skills/builder-agent-watchdog","html":"/skills/builder-agent-watchdog","markdown":"/skills/builder-agent-watchdog.md"}},{"id":"flyte-sdk-author","name":"Flyte SDK Author","tagline":"Scaffold Flyte 2 projects, tasks, workflows, launch plans","when":"Create or scaffold Flyte workflows, tasks, or apps from scratch.","license":"Apache-2.0","sourceUrl":"https://github.com/flyteorg/skills/blob/main/plugins/flyte/skills/flyte-sdk-author/SKILL.md","catch":"Loud: Flyte OSS Apache-2.0 — local/devbox $0 forever; Flyte 1 self-host on your K8s $0. Official repo: Flyte 2 distributed OSS backend is coming soon — production Flyte 2 backend today is Union.ai (paid; do not invent free forever Cloud). Distinct from ZenML CA (MLOps pipelines vs K8s-native workflow orchestration). Skills Apache-2.0.","links":{"self":"/api/skills/flyte-sdk-author","html":"/skills/flyte-sdk-author","markdown":"/skills/flyte-sdk-author.md"}},{"id":"flyte-sdk-run","name":"Flyte SDK Run","tagline":"Run Flyte 2 workflows; logs, data, run lifecycle","when":"Run Flyte 2 workflows, interact with runs and actions, retrieve logs and data, manage run lifecycle.","license":"Apache-2.0","sourceUrl":"https://github.com/flyteorg/skills/blob/main/plugins/flyte/skills/flyte-sdk-run/SKILL.md","catch":"Loud: Flyte OSS Apache-2.0 — local/devbox $0 forever; Flyte 1 self-host on your K8s $0. Official repo: Flyte 2 distributed OSS backend is coming soon — production Flyte 2 backend today is Union.ai (paid; do not invent free forever Cloud). Distinct from ZenML CA (MLOps pipelines vs K8s-native workflow orchestration). Skills Apache-2.0.","links":{"self":"/api/skills/flyte-sdk-run","html":"/skills/flyte-sdk-run","markdown":"/skills/flyte-sdk-run.md"}},{"id":"flyte-sdk-data","name":"Flyte SDK Data","tagline":"ETL, data quality, fanout/map task data patterns","when":"Data engineering patterns: ETL pipelines, data processing, data quality checks, fanout/map tasks.","license":"Apache-2.0","sourceUrl":"https://github.com/flyteorg/skills/blob/main/plugins/flyte/skills/flyte-sdk-data/SKILL.md","catch":"Loud: Flyte OSS Apache-2.0 — local/devbox $0 forever; Flyte 1 self-host on your K8s $0. Official repo: Flyte 2 distributed OSS backend is coming soon — production Flyte 2 backend today is Union.ai (paid; do not invent free forever Cloud). Distinct from ZenML CA (MLOps pipelines vs K8s-native workflow orchestration). Skills Apache-2.0.","links":{"self":"/api/skills/flyte-sdk-data","html":"/skills/flyte-sdk-data","markdown":"/skills/flyte-sdk-data.md"}},{"id":"flyte-sdk-ml","name":"Flyte SDK ML","tagline":"Training, HPO, experiment tracking on Flyte","when":"ML workload patterns: model training, hyperparameter optimization, experiment tracking.","license":"Apache-2.0","sourceUrl":"https://github.com/flyteorg/skills/blob/main/plugins/flyte/skills/flyte-sdk-ml/SKILL.md","catch":"Loud: Flyte OSS Apache-2.0 — local/devbox $0 forever; Flyte 1 self-host on your K8s $0. Official repo: Flyte 2 distributed OSS backend is coming soon — production Flyte 2 backend today is Union.ai (paid; do not invent free forever Cloud). Distinct from ZenML CA (MLOps pipelines vs K8s-native workflow orchestration). Skills Apache-2.0.","links":{"self":"/api/skills/flyte-sdk-ml","html":"/skills/flyte-sdk-ml","markdown":"/skills/flyte-sdk-ml.md"}},{"id":"flyte-sdk-ship","name":"Flyte SDK Ship","tagline":"flyte.Image specs, Dockerfiles, dependency and tagging","when":"Generate flyte.Image specs, Dockerfiles, dependency management, image tagging, reproducible ship paths.","license":"Apache-2.0","sourceUrl":"https://github.com/flyteorg/skills/blob/main/plugins/flyte/skills/flyte-sdk-ship/SKILL.md","catch":"Loud: Flyte OSS Apache-2.0 — local/devbox $0 forever; Flyte 1 self-host on your K8s $0. Official repo: Flyte 2 distributed OSS backend is coming soon — production Flyte 2 backend today is Union.ai (paid; do not invent free forever Cloud). Distinct from ZenML CA (MLOps pipelines vs K8s-native workflow orchestration). Skills Apache-2.0.","links":{"self":"/api/skills/flyte-sdk-ship","html":"/skills/flyte-sdk-ship","markdown":"/skills/flyte-sdk-ship.md"}},{"id":"running-dbt-commands","name":"Running dbt Commands","tagline":"Format and execute dbt CLI with the right executable","when":"Format and execute dbt CLI commands; select the correct dbt executable and flags.","license":"Apache-2.0","sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/blob/main/skills/dbt/skills/running-dbt-commands/SKILL.md","catch":"Loud: $0 forever path is dbt Core OSS Apache-2.0 (local/self-host). Platform Developer Free forever is real but capped (1 seat / 1 project / 3k successful models/mo); Starter $100/user/mo. Semantic Layer advanced is Cloud-paid — do not pitch Platform as the free hatch. Distinct from Flyte CD / ZenML CA. Skills Apache-2.0.","links":{"self":"/api/skills/running-dbt-commands","html":"/skills/running-dbt-commands","markdown":"/skills/running-dbt-commands.md"}},{"id":"adding-dbt-unit-test","name":"Adding dbt Unit Test","tagline":"Unit test YAML mocking upstream model inputs","when":"Create unit test YAML definitions that mock upstream model inputs and validate outputs.","license":"Apache-2.0","sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/blob/main/skills/dbt/skills/adding-dbt-unit-test/SKILL.md","catch":"Loud: $0 forever path is dbt Core OSS Apache-2.0 (local/self-host). Platform Developer Free forever is real but capped (1 seat / 1 project / 3k successful models/mo); Starter $100/user/mo. Semantic Layer advanced is Cloud-paid — do not pitch Platform as the free hatch. Distinct from Flyte CD / ZenML CA. Skills Apache-2.0.","links":{"self":"/api/skills/adding-dbt-unit-test","html":"/skills/adding-dbt-unit-test","markdown":"/skills/adding-dbt-unit-test.md"}},{"id":"building-dbt-semantic-layer","name":"Building dbt Semantic Layer","tagline":"Create or modify Semantic Layer components","when":"Create or modify dbt Semantic Layer components. Advanced Semantic Layer is Cloud-paid — Core/docs first.","license":"Apache-2.0","sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/blob/main/skills/dbt/skills/building-dbt-semantic-layer/SKILL.md","catch":"Loud: $0 forever path is dbt Core OSS Apache-2.0 (local/self-host). Platform Developer Free forever is real but capped (1 seat / 1 project / 3k successful models/mo); Starter $100/user/mo. Semantic Layer advanced is Cloud-paid — do not pitch Platform as the free hatch. Distinct from Flyte CD / ZenML CA. Skills Apache-2.0.","links":{"self":"/api/skills/building-dbt-semantic-layer","html":"/skills/building-dbt-semantic-layer","markdown":"/skills/building-dbt-semantic-layer.md"}},{"id":"configuring-dbt-mcp-server","name":"Configuring dbt MCP Server","tagline":"MCP server JSON and auth for dbt","when":"Generate MCP server configuration JSON and resolve authentication setup for dbt.","license":"Apache-2.0","sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/blob/main/skills/dbt/skills/configuring-dbt-mcp-server/SKILL.md","catch":"Loud: $0 forever path is dbt Core OSS Apache-2.0 (local/self-host). Platform Developer Free forever is real but capped (1 seat / 1 project / 3k successful models/mo); Starter $100/user/mo. Semantic Layer advanced is Cloud-paid — do not pitch Platform as the free hatch. Distinct from Flyte CD / ZenML CA. Skills Apache-2.0.","links":{"self":"/api/skills/configuring-dbt-mcp-server","html":"/skills/configuring-dbt-mcp-server","markdown":"/skills/configuring-dbt-mcp-server.md"}},{"id":"maintaining-dbt-documentation","name":"Maintaining dbt Documentation","tagline":"Audit coverage; draft missing model/column docs","when":"Audit dbt documentation coverage and draft missing model/column descriptions.","license":"Apache-2.0","sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/blob/main/skills/dbt/skills/maintaining-dbt-documentation/SKILL.md","catch":"Loud: $0 forever path is dbt Core OSS Apache-2.0 (local/self-host). Platform Developer Free forever is real but capped (1 seat / 1 project / 3k successful models/mo); Starter $100/user/mo. Semantic Layer advanced is Cloud-paid — do not pitch Platform as the free hatch. Distinct from Flyte CD / ZenML CA. Skills Apache-2.0.","links":{"self":"/api/skills/maintaining-dbt-documentation","html":"/skills/maintaining-dbt-documentation","markdown":"/skills/maintaining-dbt-documentation.md"}},{"id":"rivet-actors","name":"Rivet Actors","tagline":"Actors: the primitive for agent orchestration","when":"Use Rivet Actors as the primitive for agent orchestration.","license":"Apache-2.0","sourceUrl":"https://github.com/rivet-dev/skills/blob/main/rivet-actors/SKILL.md","catch":"Loud: Free Cloud forever hard caps (100k Awake Actor Hours / 5GB / 5M writes / 200M reads / 100GB egress / $5 compute); OSS Apache self-host uncapped $0. Hobby $20+ / Team $200+. agentOS + Dynamic Apps = Beta. Skills LICENSE 404 — product rivet-dev/rivet Apache-2.0. Distinct from Flyte/Temporal/dbt. HOLD rivet-agentos/examples/browserbase browse.","links":{"self":"/api/skills/rivet-actors","html":"/skills/rivet-actors","markdown":"/skills/rivet-actors.md"}},{"id":"rivet-agentos","name":"Rivet agentOS","tagline":"agentOS: a computer for every agent (Beta)","when":"Use Rivet agentOS — a computer for every agent. Beta.","license":"Apache-2.0","sourceUrl":"https://github.com/rivet-dev/skills/blob/main/rivet-agentos/SKILL.md","catch":"Loud: Free Cloud forever hard caps (100k Awake Actor Hours / 5GB / 5M writes / 200M reads / 100GB egress / $5 compute); OSS Apache self-host uncapped $0. Hobby $20+ / Team $200+. agentOS + Dynamic Apps = Beta. Skills LICENSE 404 — product rivet-dev/rivet Apache-2.0. Distinct from Flyte/Temporal/dbt. HOLD rivet-agentos/examples/browserbase browse.","links":{"self":"/api/skills/rivet-agentos","html":"/skills/rivet-agentos","markdown":"/skills/rivet-agentos.md"}},{"id":"rivet-dynamic-apps","name":"Rivet Dynamic Apps","tagline":"Deploy an AI-generated backend per user (Beta)","when":"Use Rivet Dynamic Apps to deploy an AI-generated backend for every user. Beta.","license":"Apache-2.0","sourceUrl":"https://github.com/rivet-dev/skills/blob/main/rivet-dynamic-apps/SKILL.md","catch":"Loud: Free Cloud forever hard caps (100k Awake Actor Hours / 5GB / 5M writes / 200M reads / 100GB egress / $5 compute); OSS Apache self-host uncapped $0. Hobby $20+ / Team $200+. agentOS + Dynamic Apps = Beta. Skills LICENSE 404 — product rivet-dev/rivet Apache-2.0. Distinct from Flyte/Temporal/dbt. HOLD rivet-agentos/examples/browserbase browse.","links":{"self":"/api/skills/rivet-dynamic-apps","html":"/skills/rivet-dynamic-apps","markdown":"/skills/rivet-dynamic-apps.md"}},{"id":"rivet-workflows","name":"Rivet Workflows","tagline":"Durable, replayable multi-step operations","when":"Use Rivet Workflows for durable, replayable multi-step operations.","license":"Apache-2.0","sourceUrl":"https://github.com/rivet-dev/skills/blob/main/rivet-workflows/SKILL.md","catch":"Loud: Free Cloud forever hard caps (100k Awake Actor Hours / 5GB / 5M writes / 200M reads / 100GB egress / $5 compute); OSS Apache self-host uncapped $0. Hobby $20+ / Team $200+. agentOS + Dynamic Apps = Beta. Skills LICENSE 404 — product rivet-dev/rivet Apache-2.0. Distinct from Flyte/Temporal/dbt. HOLD rivet-agentos/examples/browserbase browse.","links":{"self":"/api/skills/rivet-workflows","html":"/skills/rivet-workflows","markdown":"/skills/rivet-workflows.md"}},{"id":"polar-setup","name":"Polar Setup","tagline":"Interactive onboarding wizard for Polar payments","when":"Set up Polar from scratch: MCP, auth, first product, framework-specific checkout.","license":"Apache-2.0","sourceUrl":"https://github.com/polarsource/skills/blob/main/skills/setup-polar/SKILL.md","catch":"Loud: Starter Free forever $0/mo platform fee; MoR take-rate 5% + 50c/txn (+1.5% intl) still applies — not payments free. Pro $20 / Growth $100 / Scale $400 lower take-rate. OSS Apache self-host path. Skills LICENSE 404 — product polarsource/polar Apache-2.0. Polar gem already live. Distinct from Stripe Billing DIY tax and closed MoRs. Frontmatter name setup-polar.","links":{"self":"/api/skills/polar-setup","html":"/skills/polar-setup","markdown":"/skills/polar-setup.md"}},{"id":"polar-integration","name":"Polar Integration","tagline":"Checkout, Customer Portal, and Webhooks via @polar-sh/sdk","when":"Add Polar Checkout, Customer Portal, or Webhooks endpoints to a TypeScript/JavaScript app.","license":"Apache-2.0","sourceUrl":"https://github.com/polarsource/skills/blob/main/skills/polar-integration/SKILL.md","catch":"Loud: Starter Free forever $0/mo platform fee; MoR take-rate 5% + 50c/txn (+1.5% intl) still applies — not payments free. Pro $20 / Growth $100 / Scale $400 lower take-rate. OSS Apache self-host path. Skills LICENSE 404 — product polarsource/polar Apache-2.0. Polar gem already live. Distinct from Stripe Billing DIY tax and closed MoRs.","links":{"self":"/api/skills/polar-integration","html":"/skills/polar-integration","markdown":"/skills/polar-integration.md"}},{"id":"polar-migration","name":"Polar Migration","tagline":"Migrate from Stripe Billing, Paddle, Lemon Squeezy, Gumroad","when":"Plan or run a migration to Polar from another payment provider.","license":"Apache-2.0","sourceUrl":"https://github.com/polarsource/skills/blob/main/skills/polar-migration/SKILL.md","catch":"Loud: Starter Free forever $0/mo platform fee; MoR take-rate 5% + 50c/txn (+1.5% intl) still applies — not payments free. Pro $20 / Growth $100 / Scale $400 lower take-rate. OSS Apache self-host path. Skills LICENSE 404 — product polarsource/polar Apache-2.0. Polar gem already live. Distinct from Stripe Billing DIY tax and closed MoRs.","links":{"self":"/api/skills/polar-migration","html":"/skills/polar-migration","markdown":"/skills/polar-migration.md"}},{"id":"polar-testing","name":"Polar Testing","tagline":"Sandbox, test cards, webhooks, CI for Polar","when":"Test Polar integrations in sandbox: checkout, Stripe test cards, webhooks, CI.","license":"Apache-2.0","sourceUrl":"https://github.com/polarsource/skills/blob/main/skills/polar-testing/SKILL.md","catch":"Loud: Starter Free forever $0/mo platform fee; MoR take-rate 5% + 50c/txn (+1.5% intl) still applies — not payments free. Pro $20 / Growth $100 / Scale $400 lower take-rate. OSS Apache self-host path. Skills LICENSE 404 — product polarsource/polar Apache-2.0. Polar gem already live. Distinct from Stripe Billing DIY tax and closed MoRs.","links":{"self":"/api/skills/polar-testing","html":"/skills/polar-testing","markdown":"/skills/polar-testing.md"}},{"id":"gemini-api-dev","name":"Gemini API Dev","tagline":"Text, chat, multimodal, tools via Gemini API SDKs","when":"Write code that calls the Gemini API for text, chat, multimodal, image/video generation, streaming, function calling, or structured output.","license":"Apache-2.0","sourceUrl":"https://github.com/google-gemini/gemini-skills/blob/main/skills/gemini-api-dev/SKILL.md","catch":"Loud: Gemini API Free Tier is real $0 (no CC) for eligible Flash models with hard RPM/RPD caps that change — do not invent numbers. Free-tier prompts may improve Google products. Pro/paid for higher quotas and production scale; Live/Omni video burn Free caps fast. Product proprietary Google SaaS — skills Apache-2.0, API is not OSS. Distinct from Firebase BO (ai-logic HOLD).","links":{"self":"/api/skills/gemini-api-dev","html":"/skills/gemini-api-dev","markdown":"/skills/gemini-api-dev.md"}},{"id":"gemini-live-api-dev","name":"Gemini Live API Dev","tagline":"Realtime bidirectional audio/video/text streaming","when":"Build realtime bidirectional streaming apps with the Gemini Live API (WebSocket audio/video/text, VAD, ephemeral tokens).","license":"Apache-2.0","sourceUrl":"https://github.com/google-gemini/gemini-skills/blob/main/skills/gemini-live-api-dev/SKILL.md","catch":"Loud: Gemini API Free Tier is real $0 (no CC) for eligible Flash models with hard RPM/RPD caps that change — do not invent numbers. Free-tier prompts may improve Google products. Pro/paid for higher quotas and production scale; Live/Omni video burn Free caps fast. Product proprietary Google SaaS — skills Apache-2.0, API is not OSS. Distinct from Firebase BO (ai-logic HOLD).","links":{"self":"/api/skills/gemini-live-api-dev","html":"/skills/gemini-live-api-dev","markdown":"/skills/gemini-live-api-dev.md"}},{"id":"gemini-omni-flash-api","name":"Gemini Omni Flash API","tagline":"Generative video edit/gen with Omni 1.1 Flash","when":"Generative video editing, text-to-video, image-referenced video, frame transitions, and extensions with gemini-omni-1.1-flash.","license":"Apache-2.0","sourceUrl":"https://github.com/google-gemini/gemini-skills/blob/main/skills/gemini-omni-flash-api/SKILL.md","catch":"Loud: Gemini API Free Tier is real $0 (no CC) for eligible Flash models with hard RPM/RPD caps that change — do not invent numbers. Free-tier prompts may improve Google products. Pro/paid for higher quotas and production scale; Live/Omni video burn Free caps fast. Product proprietary Google SaaS — skills Apache-2.0, API is not OSS. Distinct from Firebase BO (ai-logic HOLD).","links":{"self":"/api/skills/gemini-omni-flash-api","html":"/skills/gemini-omni-flash-api","markdown":"/skills/gemini-omni-flash-api.md"}},{"id":"statsig-mcp","name":"Statsig MCP","tagline":"Inspect and manage gates, experiments, configs via Statsig MCP","when":"Use the Statsig MCP to inspect and manage gates, experiments, dynamic configs, segments, metrics, audit logs, and results.","license":"ISC","sourceUrl":"https://github.com/statsig-io/agent-skills/blob/main/skills/statsig/SKILL.md","catch":"Loud: Developer Free forever $0 no CC — 2M events/mo, unlimited seats, unlimited flag/config checks, 50k session replays/mo, 1-year analytics retention. Over Free → upgrade prompt to Pro ($150/mo + overages). Proprietary SaaS (not OSS); skills ISC. Distinct from LaunchDarkly CB and GrowthBook BC (OSS self-host). Frontmatter name statsig (parent).","links":{"self":"/api/skills/statsig-mcp","html":"/skills/statsig-mcp","markdown":"/skills/statsig-mcp.md"}},{"id":"statsig-create-cloud-metric","name":"Statsig Create Cloud Metric","tagline":"Create Cloud metrics via Console API","when":"Create Statsig Cloud metrics via Console API POST /console/v1/metrics.","license":"ISC","sourceUrl":"https://github.com/statsig-io/agent-skills/blob/main/skills/statsig-create-cloud-metric/SKILL.md","catch":"Loud: Developer Free forever $0 no CC — 2M events/mo, unlimited seats, unlimited flag/config checks, 50k session replays/mo, 1-year analytics retention. Over Free → upgrade prompt to Pro ($150/mo + overages). Proprietary SaaS (not OSS); skills ISC. Distinct from LaunchDarkly CB and GrowthBook BC (OSS self-host).","links":{"self":"/api/skills/statsig-create-cloud-metric","html":"/skills/statsig-create-cloud-metric","markdown":"/skills/statsig-create-cloud-metric.md"}},{"id":"statsig-dashboard","name":"Statsig Dashboard","tagline":"Create or read dashboards via Console API","when":"Create or read Statsig dashboards through the Console API; build or update dashboard widgets.","license":"ISC","sourceUrl":"https://github.com/statsig-io/agent-skills/blob/main/skills/statsig-dashboard/SKILL.md","catch":"Loud: Developer Free forever $0 no CC — 2M events/mo, unlimited seats, unlimited flag/config checks, 50k session replays/mo, 1-year analytics retention. Over Free → upgrade prompt to Pro ($150/mo + overages). Proprietary SaaS (not OSS); skills ISC. Distinct from LaunchDarkly CB and GrowthBook BC (OSS self-host).","links":{"self":"/api/skills/statsig-dashboard","html":"/skills/statsig-dashboard","markdown":"/skills/statsig-dashboard.md"}},{"id":"ory-local-dev","name":"Ory Local Dev","tagline":"Local Kratos/Keto/Hydra stack on :4000 without Network","when":"Develop, prototype, or test login/registration/recovery/permission flows locally — run Ory offline, no Network project yet, spin up Kratos/Keto/Hydra.","license":"Apache-2.0","sourceUrl":"https://github.com/ory/claude-plugins/blob/master/plugins/ory-agent-plugin/skills/ory-local-dev/SKILL.md","catch":"Loud: Network Developer Free $0 = PoC only (2 development envs, 0 prod/staging, 1 member). Production Network from ~$770/yr. Uncapped $0 = OSS self-host Apache-2.0 (Kratos/Keto/Hydra/Oathkeeper). Skills Apache-2.0 LICENSE 200. Aligns with Ory gem Evaluation framing. Distinct from Descope BD Cloud Free MAU. Ory gem already live.","links":{"self":"/api/skills/ory-local-dev","html":"/skills/ory-local-dev","markdown":"/skills/ory-local-dev.md"}},{"id":"ory-auth-setup","name":"Ory Auth Setup","tagline":"Ory Network auth with Elements as default UI","when":"Add login, registration, recovery, email verification, settings, or sessions to a web app on Ory Network — Elements-first UI.","license":"Apache-2.0","sourceUrl":"https://github.com/ory/claude-plugins/blob/master/plugins/ory-agent-plugin/skills/ory-auth-setup/SKILL.md","catch":"Loud: Network Developer Free $0 = PoC only (2 development envs, 0 prod/staging, 1 member). Production Network from ~$770/yr. Uncapped $0 = OSS self-host Apache-2.0. Skills Apache-2.0 LICENSE 200. Aligns with Ory gem Catch. Distinct from Descope BD Cloud Free MAU.","links":{"self":"/api/skills/ory-auth-setup","html":"/skills/ory-auth-setup","markdown":"/skills/ory-auth-setup.md"}},{"id":"ory-login-flow","name":"Ory Login Flow","tagline":"Elements pages for login, signup, recovery, settings","when":"Build a login page, sign-up form, forgot-password flow, or account settings UI with Ory Elements self-service flows.","license":"Apache-2.0","sourceUrl":"https://github.com/ory/claude-plugins/blob/master/plugins/ory-agent-plugin/skills/ory-login-flow/SKILL.md","catch":"Loud: Network Developer Free $0 = PoC only (2 development envs, 0 prod/staging, 1 member). Production Network from ~$770/yr. Uncapped $0 = OSS self-host Apache-2.0. Skills Apache-2.0 LICENSE 200. Distinct from Descope BD Cloud Free MAU.","links":{"self":"/api/skills/ory-login-flow","html":"/skills/ory-login-flow","markdown":"/skills/ory-login-flow.md"}},{"id":"ory-social-login","name":"Ory Social Login","tagline":"OIDC providers (Google, GitHub, Apple, …) on Ory","when":"Configure Sign in with Google/GitHub/Apple/Microsoft/Discord/Slack/GitLab/Facebook on an Ory-powered app with Elements UI.","license":"Apache-2.0","sourceUrl":"https://github.com/ory/claude-plugins/blob/master/plugins/ory-agent-plugin/skills/ory-social-login/SKILL.md","catch":"Loud: Network Developer Free $0 = PoC only (2 development envs, 0 prod/staging, 1 member). Production Network from ~$770/yr. Uncapped $0 = OSS self-host Apache-2.0. Skills Apache-2.0 LICENSE 200. Distinct from Descope BD Cloud Free MAU.","links":{"self":"/api/skills/ory-social-login","html":"/skills/ory-social-login","markdown":"/skills/ory-social-login.md"}},{"id":"ory-permissions-onboarding","name":"Ory Permissions Onboarding","tagline":"Agent-tool auth: observe → enforce, default-allow + deny","when":"Onboard native agent-tool authorization — connect plugin, review allowed/blocked tools, write blocks in Console, promote observe to enforce.","license":"Apache-2.0","sourceUrl":"https://github.com/ory/claude-plugins/blob/master/plugins/ory-agent-plugin/skills/ory-permissions-onboarding/SKILL.md","catch":"Loud: Network Developer Free $0 = PoC only (2 development envs, 0 prod/staging, 1 member). Production Network from ~$770/yr. Uncapped $0 = OSS self-host Apache-2.0 (incl. Keto). Skills Apache-2.0 LICENSE 200. Aligns with Ory gem Evaluation framing. Distinct from Descope BD Cloud Free MAU.","links":{"self":"/api/skills/ory-permissions-onboarding","html":"/skills/ory-permissions-onboarding","markdown":"/skills/ory-permissions-onboarding.md"}},{"id":"voltagent-create","name":"VoltAgent Create","tagline":"CLI / manual bootstrap for VoltAgent agent projects","when":"Create a new AI agent project on the VoltAgent framework — CLI setup or manual bootstrapping.","license":"MIT","sourceUrl":"https://github.com/VoltAgent/skills/blob/main/skills/create-voltagent/SKILL.md","catch":"Loud: Core Framework Free forever MIT $0 (memory/RAG/guardrails/tools/MCP/voice/workflows). VoltOps Developer Free $0/mo (1 seat / 250 traces / 7-day retention); Core $50 / Pro $250. LLM BYOK. Skills MIT LICENSE 200. Distinct from Mastra (live gem), LangChain/LangGraph, Letta/CrewAI, Vercel AI SDK. CK VOID — do not restack MongoDB. Frontmatter name create-voltagent.","links":{"self":"/api/skills/voltagent-create","html":"/skills/voltagent-create","markdown":"/skills/voltagent-create.md"}},{"id":"voltagent-best-practices","name":"VoltAgent Best Practices","tagline":"Agents vs workflows, layout, memory, servers, observability","when":"Apply VoltAgent architectural patterns — agents vs workflows, project layout, memory, servers, observability.","license":"MIT","sourceUrl":"https://github.com/VoltAgent/skills/blob/main/skills/voltagent-best-practices/SKILL.md","catch":"Loud: Core Framework Free forever MIT $0 (memory/RAG/guardrails/tools/MCP/voice/workflows). VoltOps Developer Free $0/mo (1 seat / 250 traces / 7-day retention); Core $50 / Pro $250. LLM BYOK. Skills MIT LICENSE 200. Distinct from Mastra (live gem), LangChain/LangGraph, Letta/CrewAI, Vercel AI SDK. CK VOID — do not restack MongoDB. Frontmatter name voltagent-best-practices.","links":{"self":"/api/skills/voltagent-best-practices","html":"/skills/voltagent-best-practices","markdown":"/skills/voltagent-best-practices.md"}},{"id":"voltagent-core-reference","name":"VoltAgent Core Reference","tagline":"VoltAgent class: constructor, lifecycle, runtime","when":"Look up VoltAgent class constructor options, lifecycle methods, and runtime behavior.","license":"MIT","sourceUrl":"https://github.com/VoltAgent/skills/blob/main/skills/voltagent-core-reference/SKILL.md","catch":"Loud: Core Framework Free forever MIT $0 (memory/RAG/guardrails/tools/MCP/voice/workflows). VoltOps Developer Free $0/mo (1 seat / 250 traces / 7-day retention); Core $50 / Pro $250. LLM BYOK. Skills MIT LICENSE 200. Distinct from Mastra (live gem), LangChain/LangGraph, Letta/CrewAI, Vercel AI SDK. CK VOID — do not restack MongoDB. Frontmatter name voltagent-core-reference.","links":{"self":"/api/skills/voltagent-core-reference","html":"/skills/voltagent-core-reference","markdown":"/skills/voltagent-core-reference.md"}},{"id":"voltagent-docs-bundle","name":"VoltAgent Docs Bundle","tagline":"Version-matched docs from @voltagent/core/docs","when":"Look up VoltAgent API signatures, guides, and examples from node_modules/@voltagent/core/docs (version-matched).","license":"MIT","sourceUrl":"https://github.com/VoltAgent/skills/blob/main/skills/voltagent-docs-bundle/SKILL.md","catch":"Loud: Core Framework Free forever MIT $0 (memory/RAG/guardrails/tools/MCP/voice/workflows). VoltOps Developer Free $0/mo (1 seat / 250 traces / 7-day retention); Core $50 / Pro $250. LLM BYOK. Skills MIT LICENSE 200. Distinct from Mastra (live gem), LangChain/LangGraph, Letta/CrewAI, Vercel AI SDK. CK VOID — do not restack MongoDB. Frontmatter name voltagent-docs-bundle.","links":{"self":"/api/skills/voltagent-docs-bundle","html":"/skills/voltagent-docs-bundle","markdown":"/skills/voltagent-docs-bundle.md"}},{"id":"circleci-builds","name":"CircleCI Builds","tagline":"Diagnose failing jobs and flaky pipelines","when":"Investigate failed CircleCI jobs, triage flaky pipelines, find root causes from logs, and apply minimal config/test/build fixes.","license":"MIT","sourceUrl":"https://github.com/CircleCI-Public/skills/blob/main/plugins/circleci/skills/builds/SKILL.md","catch":"Loud: Free plan $0/mo no CC — 30k credits/mo (~up to 6k small Docker mins), 5 users; Free credits expire monthly (no rollover). OSS orgs on Free up to 400k credits/mo Linux/Arm/Docker. Performance from ~$15/mo. Proprietary SaaS CI — not self-host OSS core. Skills root LICENSE 404; plugin.json MIT + circleci-cli MIT. Distinct from Buildkite BB (agent pipelines) and Flux BE (GitOps). HOLD chunk + smarter-testing. Frontmatter name circleci-builds.","links":{"self":"/api/skills/circleci-builds","html":"/skills/circleci-builds","markdown":"/skills/circleci-builds.md"}},{"id":"circleci-cli","name":"CircleCI CLI","tagline":"Auth, validate, watch runs, logs, rerun/cancel","when":"Day-to-day CircleCI from the terminal — authenticate, validate config, watch a run, read logs/failed tests, download artifacts, rerun or cancel.","license":"MIT","sourceUrl":"https://github.com/CircleCI-Public/skills/blob/main/plugins/circleci/skills/cli/SKILL.md","catch":"Loud: Free plan $0/mo no CC — 30k credits/mo (~up to 6k small Docker mins), 5 users; Free credits expire monthly (no rollover). OSS orgs on Free up to 400k credits/mo Linux/Arm/Docker. Performance from ~$15/mo. Proprietary SaaS CI — not self-host OSS core. Skills root LICENSE 404; plugin.json MIT + circleci-cli MIT. Distinct from Buildkite BB (agent pipelines) and Flux BE (GitOps). HOLD chunk + smarter-testing. Frontmatter name circleci-cli.","links":{"self":"/api/skills/circleci-cli","html":"/skills/circleci-cli","markdown":"/skills/circleci-cli.md"}},{"id":"circleci-config","name":"CircleCI Config","tagline":"Optimize .circleci/config.yml cache and parallelism","when":"Improve `.circleci/config.yml` for speed and reliability — caching, workspaces, parallelism, or config-caused flake.","license":"MIT","sourceUrl":"https://github.com/CircleCI-Public/skills/blob/main/plugins/circleci/skills/config/SKILL.md","catch":"Loud: Free plan $0/mo no CC — 30k credits/mo (~up to 6k small Docker mins), 5 users; Free credits expire monthly (no rollover). OSS orgs on Free up to 400k credits/mo Linux/Arm/Docker. Performance from ~$15/mo. Proprietary SaaS CI — not self-host OSS core. Skills root LICENSE 404; plugin.json MIT + circleci-cli MIT. Distinct from Buildkite BB (agent pipelines) and Flux BE (GitOps). HOLD chunk + smarter-testing. Frontmatter name circleci-config.","links":{"self":"/api/skills/circleci-config","html":"/skills/circleci-config","markdown":"/skills/circleci-config.md"}},{"id":"circleci-onboard","name":"CircleCI Onboard","tagline":"Account → org → GitHub App → project → pipeline","when":"First-time CircleCI setup — account, org, GitHub App, project, pipeline definition, iterate config until it passes.","license":"MIT","sourceUrl":"https://github.com/CircleCI-Public/skills/blob/main/plugins/circleci/skills/onboard/SKILL.md","catch":"Loud: Free plan $0/mo no CC — 30k credits/mo (~up to 6k small Docker mins), 5 users; Free credits expire monthly (no rollover). OSS orgs on Free up to 400k credits/mo Linux/Arm/Docker. Performance from ~$15/mo. Proprietary SaaS CI — not self-host OSS core. Skills root LICENSE 404; plugin.json MIT + circleci-cli MIT. Distinct from Buildkite BB (agent pipelines) and Flux BE (GitOps). HOLD chunk + smarter-testing. Frontmatter name onboarding.","links":{"self":"/api/skills/circleci-onboard","html":"/skills/circleci-onboard","markdown":"/skills/circleci-onboard.md"}},{"id":"circleci-testsuite","name":"CircleCI Testsuite","tagline":".circleci/test-suites.yml + testsuite doctor","when":"Onboard or migrate tests onto CircleCI testsuite (`.circleci/test-suites.yml` + `circleci testsuite run`) via testsuite doctor — not paid smarter-testing features.","license":"MIT","sourceUrl":"https://github.com/CircleCI-Public/skills/blob/main/plugins/circleci/skills/testsuite/SKILL.md","catch":"Loud: Free plan $0/mo no CC — 30k credits/mo (~up to 6k small Docker mins), 5 users; Free credits expire monthly (no rollover). OSS orgs on Free up to 400k credits/mo Linux/Arm/Docker. Performance from ~$15/mo. Proprietary SaaS CI — not self-host OSS core. Skills root LICENSE 404; plugin.json MIT + circleci-cli MIT. Distinct from Buildkite BB (agent pipelines) and Flux BE (GitOps). HOLD chunk + smarter-testing. Frontmatter name circleci-testsuite.","links":{"self":"/api/skills/circleci-testsuite","html":"/skills/circleci-testsuite","markdown":"/skills/circleci-testsuite.md"}},{"id":"xata-using-api","name":"Xata Using API","tagline":"HTTP API for orgs, projects, branches, auth","when":"Call the Xata HTTP API (curl/fetch/SDK) to manage orgs, projects, branches, auth, connection strings, pagination, and errors.","license":"Apache-2.0","sourceUrl":"https://github.com/xataio/skills/blob/main/skills/using-xata-api/SKILL.md","catch":"Loud: $0 forever path is Open Source self-host (branching/scale-to-zero) — verified xata.io/pricing. Xata Cloud is 14-day free trial then PAYG from ~$0.012/hr + $0.28/GB/mo storage — not a forever free Cloud hatch. Skills Apache-2.0 LICENSE 200. Distinct from Neon/Supabase/Postgres gems and Redis BH. Frontmatter name using-xata-api.","links":{"self":"/api/skills/xata-using-api","html":"/skills/xata-using-api","markdown":"/skills/xata-using-api.md"}},{"id":"xata-using-cli","name":"Xata Using CLI","tagline":"xata CLI, pgroll, scratch branches, metrics","when":"Manage Xata via the xata CLI — projects, branches, pgroll migrations, scratch branches, metrics, logs, connection strings.","license":"Apache-2.0","sourceUrl":"https://github.com/xataio/skills/blob/main/skills/using-xata-cli/SKILL.md","catch":"Loud: $0 forever path is Open Source self-host (branching/scale-to-zero) — verified xata.io/pricing. Xata Cloud is 14-day free trial then PAYG from ~$0.012/hr + $0.28/GB/mo storage — not a forever free Cloud hatch. Skills Apache-2.0 LICENSE 200. Distinct from Neon/Supabase/Postgres gems and Redis BH. Frontmatter name using-xata-cli.","links":{"self":"/api/skills/xata-using-cli","html":"/skills/xata-using-cli","markdown":"/skills/xata-using-cli.md"}},{"id":"xata-managing-postgresql","name":"Xata Managing PostgreSQL","tagline":"PG ops and performance in a Xata branch","when":"Diagnose PostgreSQL issues in a Xata branch context — slow queries, locks, vacuum, indexes, connections, replication, backups.","license":"Apache-2.0","sourceUrl":"https://github.com/xataio/skills/blob/main/skills/managing-postgresql/SKILL.md","catch":"Loud: $0 forever path is Open Source self-host (branching/scale-to-zero) — verified xata.io/pricing. Xata Cloud is 14-day free trial then PAYG from ~$0.012/hr + $0.28/GB/mo storage — not a forever free Cloud hatch. Skills Apache-2.0 LICENSE 200. Distinct from Neon/Supabase/Postgres gems and Redis BH. Frontmatter name managing-postgresql.","links":{"self":"/api/skills/xata-managing-postgresql","html":"/skills/xata-managing-postgresql","markdown":"/skills/xata-managing-postgresql.md"}}],"meta":{"total":494,"count":494}}