{"data":[{"slug":"google-workspace-cli","name":"Google Workspace CLI","tagline":"Apache-2.0 first-party gws CLI — Drive, Gmail, Calendar, agent skills","category":"agents","url":"https://github.com/googleworkspace/cli","github":"https://github.com/googleworkspace/cli","pricing":"open-source","hook":"gws is the Google Workspace CLI from the googleworkspace org — one dynamic command surface for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and agent skills.","whatsGood":"Apache-2.0 (googleworkspace/cli). Commands built at runtime from Google Discovery Service — new Workspace methods show up without a static command list. Structured JSON, `--dry-run`, agent skills pack, npm `@googleworkspace/cli`, Homebrew `googleworkspace-cli`, binary releases. Built for humans and AI agents sharing the same auth’d surface.","theCatch":"First-party googleworkspace org surface — but the README states it is not an officially supported Google product. Vs raw Workspace REST / Apps Script: this is the CLI/agent skill layer, not a new API. Needs a GCP project + OAuth; unverified apps hit scope limits; Workspace/Admin API quotas still apply.","verdict":"Apache-2.0 Workspace CLI. First-party org tooling for agents; not a Google support SLA.","addedAt":"2026-09-15","featured":false,"domain":"AI Agents","subSpecialty":"Tooling","subcategory":"Skills","tags":["cli","self-host","permissive","skills","active","fast-stars"],"capabilities":["cli","workspace","agents"],"surfaces":["CLI","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"Apache-2.0","githubStars":31660,"starsPerWeek":957,"access":"free","archived":false,"repo":{"createdAt":"2026-03-02","pushedAt":"2026-10-06","license":"Apache-2.0","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/google-workspace-cli","html":"/gems/google-workspace-cli","markdown":"/gems/google-workspace-cli.md"}},{"slug":"superpowers","name":"Superpowers","tagline":"Composable agent skills that force brainstorm → plan → TDD → subagent review","category":"agents","url":"https://github.com/obra/superpowers","github":"https://github.com/obra/superpowers","pricing":"open-source","hook":"Superpowers makes your coding agent stop vibing and follow a real engineering loop before it touches the repo.","whatsGood":"MIT (obra/superpowers). A skills pack plus harness hooks so Claude Code, Cursor, Codex, OpenCode, Hermes, Gemini CLI, and peers brainstorm a design, write a bite-sized plan, then run subagent-driven development with red/green TDD and two-stage review. Install paths are first-class per harness (official Claude/Codex marketplaces, `/add-plugin`, `agy plugin install`, etc.). ★~288k with heavy forks — the viral agent-skills methodology, not a one-off prompt dump.","theCatch":"You still need a strong coding harness and model budget; Superpowers is process, not an agent runtime. Optional visual-companion telemetry (opt out via SUPERPOWERS_DISABLE_TELEMETRY / Claude DisableTelemetry). Vs agent-skills (Addy Osmani lifecycle pack) and ECC (multi-host skill ecosystem): Superpowers is the opinionated SDLC methodology that hijacks the session start, not a general skill library or host-agnostic plugin bag.","verdict":"MIT agent methodology. Install when your agent skips specs and tests; not a replacement for the harness itself.","addedAt":"2026-09-17","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["self-host","permissive","coding-agents","skills","active","fast-stars"],"capabilities":[],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":301734,"starsPerWeek":5624,"access":"free","archived":false,"repo":{"createdAt":"2025-10-09","pushedAt":"2026-10-10","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/superpowers","html":"/gems/superpowers","markdown":"/gems/superpowers.md"}},{"slug":"agent-skills","name":"Agent Skills (Addy Osmani)","tagline":"Production lifecycle skills — /spec /plan /build /test /review /ship","category":"agents","url":"https://skills.addy.ie","github":"https://github.com/addyosmani/agent-skills","pricing":"open-source","hook":"Addy’s Agent Skills encode senior-engineer gates so coding agents cannot skip the boring parts that keep software shippable.","whatsGood":"MIT (addyosmani/agent-skills). ~25 structured SKILL.md workflows with anti-rationalization tables and verification exits, plus slash commands mapping define→plan→build→verify→review→ship. `npx skills add addyosmani/agent-skills` hits 70+ agents; Claude/Codex/Cursor/Gemini/Antigravity adapters documented. Draws explicitly from Google eng practices (Hyrum’s Law, Beyoncé Rule, change sizing). Docs and site at skills.addy.ie. ★~96k.","theCatch":"Per-skill installs can miss shared `references/` checklists — prefer whole-repo or full pack install. Still markdown discipline, not a runtime that forces compliance if the host ignores skills. Vs Superpowers (session-hijacking SDLC methodology) and knowledge-work-plugins (Anthropic official packs): this is the Google-flavored lifecycle library you pick skill-by-skill, not an automatic brainstorm→subagent loop.","verdict":"MIT production skill pack. Reach for it when you want explicit /spec→/ship gates across many harnesses.","addedAt":"2026-09-17","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["self-host","permissive","coding-agents","skills","testing","active","fast-stars"],"capabilities":[],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":108281,"starsPerWeek":3074,"access":"free","archived":false,"repo":{"createdAt":"2026-02-15","pushedAt":"2026-10-13","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/agent-skills","html":"/gems/agent-skills","markdown":"/gems/agent-skills.md"}},{"slug":"archify","name":"Archify","tagline":"MIT agent skill that renders architecture and workflow diagrams as self-contained HTML","category":"agents","url":"https://github.com/tt-a1i/archify","github":"https://github.com/tt-a1i/archify","pricing":"open-source","hook":"Archify turns an agent skill into self-contained HTML architecture, workflow, and sequence diagrams that can travel with the project instead of living in a hosted viewer.","whatsGood":"MIT (tt-a1i/archify). The output is a portable HTML artifact for architecture, workflow, and sequence views, giving an agent a repeatable diagram surface without requiring a separate diagramming SaaS. Self-contained output is the practical wedge: inspect or share the file wherever the repo goes.","theCatch":"Vs GitDiagram: Archify is an agent skill that renders requested architecture/workflow/sequence views as self-contained HTML, while GitDiagram is a repo-to-interactive-diagram product. Diagram output is an orientation aid, not proof that every dependency or runtime relationship is correct; verify it against the source before using it as an architecture contract.","verdict":"MIT agent diagram skill. Handy portable HTML for architecture/workflow/sequence views; validate generated relationships against the code.","addedAt":"2026-09-20","featured":false,"domain":"AI Agents","subSpecialty":"Tooling","subcategory":"Skills","tags":["self-host","permissive","skills","workflows","active","fast-stars"],"capabilities":["diagrams","skills","html"],"surfaces":["Self-host","Hosted"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":85494,"starsPerWeek":3190,"access":"free","archived":false,"repo":{"createdAt":"2026-04-15","pushedAt":"2026-10-19","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/archify","html":"/gems/archify","markdown":"/gems/archify.md"}},{"slug":"stitch-skills","name":"Stitch Skills","tagline":"Google Labs agent skills and plugins for the Stitch design MCP","category":"agents","url":"https://stitch.withgoogle.com","github":"https://github.com/google-labs-code/stitch-skills","pricing":"open-source","hook":"Stitch Skills packages Agent Skills-standard plugins so coding agents can design and build against Google Stitch instead of inventing UI from scratch.","whatsGood":"Apache-2.0 (google-labs-code/stitch-skills). Follows the Agent Skills open standard with plugin packs (design, build, utilities) installable into Codex, Claude Code, Cursor, Gemini CLI, Antigravity, and OpenCode. Pairs agents with the Stitch MCP/design surface rather than leaving UI generation unguided.","theCatch":"Vs generic agent-skills packs: this library is Stitch-specific — useful when you are on Google Stitch, not a universal design system. Stitch product access and quotas remain Google-side constraints; the skills repo does not replace that.","verdict":"Apache-2.0 Stitch-oriented agent skills. Use when coding agents should drive Google Stitch design/build flows.","addedAt":"2026-09-20","featured":false,"domain":"AI Agents","subSpecialty":"Tooling","subcategory":"Skills","tags":["mcp","self-host","permissive","coding-agents","skills","active"],"capabilities":["skills","design","mcp"],"surfaces":["MCP","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"Apache-2.0","githubStars":8546,"starsPerWeek":216,"access":"free","archived":false,"repo":{"createdAt":"2026-01-16","pushedAt":"2026-08-17","license":"Apache-2.0","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/stitch-skills","html":"/gems/stitch-skills","markdown":"/gems/stitch-skills.md"}},{"slug":"skillbox","name":"Skillbox","tagline":"Self-hosted versioned skills library with MCP and scoped clients","category":"agents","url":"https://github.com/kitze/skillbox","github":"https://github.com/kitze/skillbox","pricing":"open-source","hook":"Skillbox is a self-hosted skills registry for AI agents — versioned skills, scoped client keys, HTTP MCP, and a Docker-first setup script.","whatsGood":"MIT (kitze/skillbox). React/Bun/Hono/PostgreSQL stack with admin token auth, per-client grants, checksum-verified CLI downloads, stdio bridge, and optional Jev recommendations. Umbrel packaging and documented LAN/HTTPS self-host paths make it an operator surface, not only a folder of SKILL.md files.","theCatch":"Vs Addy Agent Skills / Stitch Skills: Skillbox is the self-hosted library and MCP distribution plane, not a content pack of engineering or Stitch-specific skills. You run Postgres (or Docker Compose) and guard SKILLBOX_ADMIN_TOKEN; optional Jev tips inherit TypeSafe pricing.","verdict":"MIT self-hosted skills library. Use when multiple agents need a versioned, scoped skill source you control.","addedAt":"2026-09-21","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["mcp","api","sdk","self-host","permissive","skills","containers","active","young-repo"],"capabilities":["mcp"],"surfaces":["MCP","API","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":272,"starsPerWeek":58,"access":"free","archived":false,"repo":{"createdAt":"2026-09-17","pushedAt":"2026-10-09","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/skillbox","html":"/gems/skillbox","markdown":"/gems/skillbox.md"}},{"slug":"humanizer","name":"Humanizer","tagline":"Agent skill that rewrites AI-sounding prose without changing the meaning","category":"agents","url":"https://github.com/blader/humanizer","github":"https://github.com/blader/humanizer","pricing":"open-source","hook":"Humanizer is a Markdown agent skill that strips AI-sounding cadence from text while keeping the claims intact.","whatsGood":"MIT (blader/humanizer). Install with `npx skills add blader/humanizer`, Claude Code plugin paths, or a manual SKILL.md copy — works on any host that loads Agent Skills. Optional voice-matching from your own sample paragraphs. Trending hard as a portable /humanizer workflow rather than a hosted rewriter.","theCatch":"Vs Caveman: Humanizer targets human-sounding prose; Caveman targets terse token compression for coding agents — different jobs. \"sounds human\" is still model-dependent taste; keep a human pass on legal/compliance copy.","verdict":"MIT Agent Skills pack for de-AI prose. Reach for /humanizer when drafts read like a model wrote them.","addedAt":"2026-09-21","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["self-host","permissive","skills","active","fast-stars"],"capabilities":[],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":58181,"starsPerWeek":1483,"access":"free","archived":false,"repo":{"createdAt":"2026-01-18","pushedAt":"2026-10-16","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/humanizer","html":"/gems/humanizer","markdown":"/gems/humanizer.md"}},{"slug":"video-use","name":"video-use","tagline":"Video-editing skill stack for coding agents","category":"agents","url":"https://github.com/browser-use/video-use","github":"https://github.com/browser-use/video-use","pricing":"open-source","hook":"video-use gives a coding agent a local video-editing skill stack instead of asking a browser agent to improvise a timeline.","whatsGood":"MIT. Clone the repo, install locally with uv or pip, and put the skills alongside a shell, FFmpeg, and the media files the agent needs. The appeal is an inspectable, composable workflow for cutting and transforming video rather than a closed editor that hides every step behind a hosted UI.","theCatch":"Vs HyperFrames and Browser Use: video-use is a video-editing skill stack, not browser automation or a general web-use agent. The useful path needs shell access and FFmpeg, and transcription needs ElevenLabs unless you supply another compatible route; Cloud is optional, but the local setup is not zero-dependency or zero-credential.","verdict":"MIT local video-editing skills for coding agents. Keep it when you want inspectable FFmpeg workflows; do not mistake it for a browser agent or a turnkey editor.","addedAt":"2026-09-23","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["cli","self-host","permissive","coding-agents","browser-automation","skills","active","fast-stars"],"capabilities":["video","skills","cli"],"surfaces":["CLI","Self-host"],"ecosystem":["Python","Multi-platform"],"licenseModel":"OSS/MIT","githubStars":29292,"starsPerWeek":1076,"access":"free","archived":false,"repo":{"createdAt":"2026-04-12","pushedAt":"2026-10-08","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/video-use","html":"/gems/video-use","markdown":"/gems/video-use.md"}},{"slug":"impeccable","name":"Impeccable","tagline":"Apache design language/skills that make AI harnesses better at UI","category":"agents","url":"https://impeccable.style","github":"https://github.com/pbakaus/impeccable","pricing":"open-source","hook":"Impeccable is a design skill + command set for AI coding harnesses: PRODUCT.md truth, 24 /impeccable commands, and 61 deterministic detectors so agents stop shipping Inter-and-purple defaults.","whatsGood":"Apache-2.0 (pbakaus/impeccable). One skill covers craft/init/audit/polish and more; CLI and browser extension run deterministic rules with no LLM key. Installs into Claude Code, Cursor, Codex, Grok, Hermes, and peers via `npx impeccable install`; docs at impeccable.style.","theCatch":"Vs Superpowers and agent-skills packs: Impeccable is a design-language/skills layer for UI quality, not a coding agent and not a general agent-skills monorepo. Node ≥22.18 for the npx installer path; star count is extreme (~70k) — treat momentum as discovery noise until the skill actually changes your harness output.","verdict":"Apache design skill when your coding agent ships samey SaaS UI and you want PRODUCT.md + detectors in-loop; not a substitute for an agent runtime.","addedAt":"2026-09-24","featured":false,"domain":"AI Agents","subSpecialty":"Tooling","subcategory":"Skills","tags":["self-host","permissive","coding-agents","skills","active","fast-stars"],"capabilities":["skills","design","ui"],"surfaces":["Self-host"],"ecosystem":["Node.js","Multi-platform"],"licenseModel":"Apache-2.0","githubStars":82786,"starsPerWeek":1717,"access":"free","archived":false,"repo":{"createdAt":"2025-11-16","pushedAt":"2026-10-19","license":"Apache-2.0","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/impeccable","html":"/gems/impeccable","markdown":"/gems/impeccable.md"}},{"slug":"anti-slop","name":"antislop","tagline":"MIT skill/rules that filter generic AI UI and copy — not a style guide","category":"agents","url":"https://github.com/miqdadbadjuber/anti-slop","github":"https://github.com/miqdadbadjuber/anti-slop","pricing":"open-source","hook":"antislop is a filter skill for coding agents: 38 mandatory rules plus a Delivery Gate so generated UI and copy stop reading like generic AI slop — without prescribing colors or fonts.","whatsGood":"MIT (miqdadbadjuber/anti-slop). Hard Gate / Purpose-Gate / Quality Locks tiers, Liveliness Toolkit (ENERGY/RHYTHM/MOTION), additive per-concern skills, skills.sh install path. DESIGN.md (yours) supplies direction; the filter refuses invented stats and sparkle-default chrome.","theCatch":"Vs Impeccable: antislop is a slop filter + PASS/FAIL delivery gate, not a design-language skill with craft commands and deterministic detectors. Without your own DESIGN.md the output can be honest but plain (R-37); it does not beautify on its own.","verdict":"MIT anti-slop skill when agents invent metrics and Inter-purple SaaS chrome; pair with DESIGN.md (or Impeccable) if you also need positive design direction.","addedAt":"2026-09-24","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["self-host","permissive","coding-agents","skills","active","young-repo","fast-stars"],"capabilities":[],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":6465,"starsPerWeek":615,"access":"free","archived":false,"repo":{"createdAt":"2026-08-07","pushedAt":"2026-10-16","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/anti-slop","html":"/gems/anti-slop","markdown":"/gems/anti-slop.md"}},{"slug":"unlazy","name":"unlazy","tagline":"MIT anti-laziness Depth Tree skill — gates, evidence, reverify","category":"agents","url":"https://github.com/Leonxlnx/unlazy","github":"https://github.com/Leonxlnx/unlazy","pricing":"open-source","hook":"unlazy is a completion-discipline skill for substantial agent work: write an acceptance ledger first, run reviewed CHECK gates, reverify returned work, and report only what evidence supports.","whatsGood":"MIT (Leonxlnx/unlazy). Install via `npx skills add Leonxlnx/unlazy`. Core SKILL.md plus Node gate-check (no third-party runtime deps). Depth Tree / scoped pipeline under `.unlazy/<scope>/`, approval store outside the repo, `--status` dry path and `--reverify` parent checks. Research-grounded laziness/underthinking framing.","theCatch":"Vs generic “be thorough” prompt packs: unlazy is a runnable gate contract with evidence fingerprints, not vibes. CHECK lines are shell — approval is consent, not a sandbox; pin a commit (2.1.0 source may be unreleased as a tag); Windows shell/PATH mismatches fail verification for real.","verdict":"MIT Depth Tree / gates skill when agents declare done without evidence; skip if you only needed a shorter system prompt.","addedAt":"2026-09-24","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["self-host","permissive","skills","active","young-repo"],"capabilities":[],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":3990,"starsPerWeek":390,"access":"free","archived":false,"repo":{"createdAt":"2026-08-09","pushedAt":"2026-09-03","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/unlazy","html":"/gems/unlazy","markdown":"/gems/unlazy.md"}},{"slug":"cc-switch","name":"CC Switch","tagline":"MIT desktop All-in-One manager for Claude Code, Codex, OpenCode, and peers","category":"agents","url":"https://ccswitch.io","github":"https://github.com/farion1231/cc-switch","pricing":"open-source","hook":"CC Switch is a Tauri desktop All-in-One for Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes, and MiniMax Code — providers, MCP, and skills in one SQLite-backed UI.","whatsGood":"MIT (farion1231/cc-switch). 50+ provider presets, tray quick-switch, unified MCP/Skills management, cloud sync via Dropbox/OneDrive/iCloud/WebDAV, atomic config writes. Official site ccswitch.io; Windows/macOS/Linux releases.","theCatch":"Vs editing each harness config by hand or using a single-vendor settings UI: CC Switch is a cross-harness desktop manager, not a coding agent and not an API gateway. Extreme star velocity (~136k aria-label) and a long sponsor/relay block on the README — treat momentum and affiliate banners as noise; verify releases from the GitHub/ccswitch.io path you trust.","verdict":"MIT desktop switchboard when you juggle many coding-agent configs and MCP/skills; skip if you live in one harness with one provider.","addedAt":"2026-09-24","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["mcp","cli","desktop-app","self-host","permissive","coding-agents","skills","active","fast-stars"],"capabilities":["mcp","cli"],"surfaces":["MCP","CLI","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":146007,"starsPerWeek":2315,"access":"free","archived":false,"repo":{"createdAt":"2025-08-04","pushedAt":"2026-10-19","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/cc-switch","html":"/gems/cc-switch","markdown":"/gems/cc-switch.md"}},{"slug":"financial-services","name":"Claude for Financial Services","tagline":"Apache-2.0 finance reference agents/skills (Anthropic)","category":"agents","url":"https://github.com/anthropics/financial-services","github":"https://github.com/anthropics/financial-services","pricing":"open-source","hook":"Anthropic’s financial-services repo ships reference agents, skills, and data connectors for IB, equity research, PE, and wealth workflows — same pack for Claude Cowork plugins or Managed Agents API.","whatsGood":"Apache-2.0 (anthropics/financial-services). Free to read/fork: system prompts, skills, and connectors shaped for analyst work product (models, memos, research notes) under human review. Install as Cowork plugins or deploy via Managed Agents. ★37,903 on GitHub 2026-09-28.","theCatch":"Vs Knowledge Work Plugins: that pack is general knowledge-work/Cowork; this tree is finance-domain only. Not investment/legal/tax advice — drafts for qualified humans. Intended hosts are Claude Cowork / Managed Agents (paid Anthropic surfaces); the repo is free, the runtime usually is not.","verdict":"Apache-2.0 Anthropic finance agent pack when IB/ER/PE workflows need first-party skills — not general knowledge-work plugins; paid host likely.","addedAt":"2026-09-28","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["api","self-host","permissive","skills","workflows","active","fast-stars"],"capabilities":["api"],"surfaces":["API","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"Apache-2.0","githubStars":40304,"starsPerWeek":1183,"access":"free","archived":false,"repo":{"createdAt":"2026-02-23","pushedAt":"2026-09-21","license":"Apache-2.0","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/financial-services","html":"/gems/financial-services","markdown":"/gems/financial-services.md"}},{"slug":"mattpocock-skills","name":"Matt Pocock Skills","tagline":"MIT composable SKILL.md pack for real engineering — not vibe coding","category":"agents","url":"https://aihero.dev/skills","github":"https://github.com/mattpocock/skills","pricing":"open-source","hook":"Matt Pocock’s skills pack turns coding agents into grilled, TDD-aware engineers — small composable SKILL.md workflows instead of a process framework that owns your loop.","whatsGood":"MIT (mattpocock/skills). Daily-driver agent skills from Matt’s `.agents` directory: `/grill-me`, `/grill-with-docs`, `/tdd`, `/to-spec`, `/implement`, architecture deepeners, and productivity handoffs. Install via `npx skills@latest add mattpocock/skills` (skills.sh / editable copies) or Claude Code plugin `mattpocock-skills` (managed marketplace bundle). Designed to stay small, adaptable, and model-agnostic — engineering fundamentals encoded as skills, not a BMAD/GSD-style process takeover.","theCatch":"Star counts on viral skill repos are a weak signal (watchers are far below stars here); judge it on substance, not the counter. Vs agent-skills (Addy Osmani `/spec→/ship` lifecycle pack) and Superpowers (session-hijacking brainstorm→plan→TDD methodology): this is Matt’s composable engineering/productivity skill library you pick and adapt, not a Google-flavored lifecycle gate set and not an automatic SDLC hijack. Installing both the Claude plugin and skills.sh copies doubles every skill — pick one path.","verdict":"MIT real-engineering skill pack when agents need grilling, TDD, and deep-module habits — rank the workflows, not the ★ counter.","addedAt":"2026-09-29","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["self-host","permissive","coding-agents","skills","workflows","active","fast-stars"],"capabilities":["skills","engineering","agents"],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":296461,"starsPerWeek":8025,"access":"free","archived":false,"repo":{"createdAt":"2026-02-03","pushedAt":"2026-10-13","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/mattpocock-skills","html":"/gems/mattpocock-skills","markdown":"/gems/mattpocock-skills.md"}},{"slug":"ponytail","name":"Ponytail","tagline":"MIT “laziest senior” skill — measured LOC/token/cost cuts, not vibes","category":"agents","url":"https://github.com/DietrichGebert/ponytail","github":"https://github.com/DietrichGebert/ponytail","pricing":"open-source","hook":"Ponytail puts the silent senior who deletes fifty lines into your coding agent — with published LOC/token/cost benches, not a “be terse” meme.","whatsGood":"MIT (DietrichGebert/ponytail). Skill/plugin that pushes agents toward the smallest safe change (native `<input type=\"date\">` over a date-picker library). Published agentic benches on a real FastAPI+React repo claim ~54% mean LOC cut, ~20% cheaper, ~27% faster, 100% safety vs no-skill baseline; npm `@dietrichgebert/ponytail` plus OpenClaw/Claude/Cursor install paths. Reproduce scripts live in-repo.","theCatch":"Same inflated-★ caution as other viral skill packs — rank the benches and diffs, not the counter. Vs Caveman (terse-prose / token-compression skill+proxy, BSL engine bits) and anti-slop (UI/copy slop filter + delivery gate): Ponytail is YAGNI/minimal-implementation discipline with published LOC/cost benches, not output-style compression and not a design-slop filter. Waitlist banner (“Something’s coming”) is a future tease at ponytail.dev/soon — not a paid wall on the MIT skill.","verdict":"MIT laziest-senior skill when agents over-build; trust the published benches over the ★ count — waitlist is tease, not tollbooth.","addedAt":"2026-09-29","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["self-host","permissive","coding-agents","skills","active","young-repo","fast-stars"],"capabilities":["skills","yagni","tokens"],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":167213,"starsPerWeek":9033,"access":"free","archived":false,"repo":{"createdAt":"2026-06-12","pushedAt":"2026-10-18","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/ponytail","html":"/gems/ponytail","markdown":"/gems/ponytail.md"}},{"slug":"skillopt","name":"SkillOpt","tagline":"MIT skills optimizer — trains skill.md as params for frozen agents","category":"agents","url":"https://microsoft.github.io/SkillOpt/docs/","github":"https://github.com/microsoft/SkillOpt","pricing":"open-source","hook":"SkillOpt turns agent skill documents into trainable parameters — rollout, reflect, gated update — without touching model weights or renting a skills SaaS.","whatsGood":"MIT (microsoft/SkillOpt). `pip install skillopt` (PyPI) plus research checkout path. Treats `best_skill.md` as the adapter: trajectory-driven edits, textual learning-rate budget, validation gate, deployable artifact. BYO LLM backends (OpenAI/Azure/Claude/Qwen/…). SkillOpt-Sleep companion for offline session harvest. Not a paid wall — bring your own keys and verifiers.","theCatch":"★17,883 in about 70 weeks (~255 a week): judge it on the optimizer loop, not the star count. Vs Superpowers / agent-skills (Addy) / Matt Pocock skills packs: those ship hand-authored SKILL.md workflows and session methodology; SkillOpt trains/evolves skills as parameters for frozen agents. Training burns provider tokens; plugin shells for Claude/Codex/etc. live in-repo more than in the PyPI wheel.","verdict":"MIT skill trainer when frozen agents need evolved skill.md — not another hand-pack; ignore the star spike.","addedAt":"2026-09-30","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["self-host","local-first","permissive","skills","active","young-repo","fast-stars"],"capabilities":["skills","optimizer","agents"],"surfaces":["Self-host","Hosted"],"ecosystem":["Python","Multi-platform"],"licenseModel":"OSS/MIT","githubStars":18545,"starsPerWeek":789,"access":"free","archived":false,"repo":{"createdAt":"2026-05-08","pushedAt":"2026-10-18","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/skillopt","html":"/gems/skillopt","markdown":"/gems/skillopt.md"}},{"slug":"bmad-method","name":"BMAD Method","tagline":"MIT agent skills method — npm bmad-method, not proprietary","category":"agents","url":"https://github.com/bmad-code-org/BMAD-METHOD","github":"https://github.com/bmad-code-org/BMAD-METHOD","pricing":"open-source","hook":"BMAD Method is a MIT skills methodology pack for agent workflows — install `bmad-method` and run structured skill loops without inventing another hand-rolled SKILL.md cult.","whatsGood":"MIT (bmad-code-org/BMAD-METHOD). Raw LICENSE is MIT plus a trademark notice; GitHub API NOASSERTION is a classifier artifact — not a proprietary license. npm `bmad-method` resolves MIT (HTTP 200). Skills-well shaped for coding-agent harnesses.","theCatch":"★53681 in about 417 weeks (~129 a week): judge it on the method/skills substance, not the star count. Vs mattpocock-skills / agent-skills (Addy): those are engineering skills packs and production lifecycle /spec→/ship skills — BMAD’s catch is the BMAD Method skills methodology + npm package, not Matt’s pack and not Addy’s lifecycle commands. TM notice is branding, not a license wall; still verify which harnesses load the skills first-class.","verdict":"MIT skills method when agents need BMAD’s structured loops — not mattpocock-skills / Addy agent-skills; treat the star spike with caution.","addedAt":"2026-10-01","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["self-host","permissive","license-unclear","skills","workflows","active","fast-stars"],"capabilities":["skills","methodology","agents"],"surfaces":["Self-host"],"ecosystem":["Node.js","Multi-platform"],"licenseModel":"OSS/MIT","githubStars":54311,"starsPerWeek":686,"access":"free","archived":false,"repo":{"createdAt":"2025-04-13","pushedAt":"2026-10-19","license":"NOASSERTION","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/bmad-method","html":"/gems/bmad-method","markdown":"/gems/bmad-method.md"}},{"slug":"vercel-skills","name":"Skills (Vercel Labs)","tagline":"MIT open agent-skills CLI — npx skills, skills.sh ecosystem","category":"agents","url":"https://skills.sh","github":"https://github.com/vercel-labs/skills","pricing":"open-source","hook":"Vercel Labs’ Skills is the open agent-skills CLI — `npx skills` installs and manages skills across OpenCode, Claude Code, Codex, Cursor, and dozens more harnesses from one ecosystem.","whatsGood":"MIT (vercel-labs/skills). npm `skills` (HTTP 200). CLI for the open agent skills ecosystem with skills.sh as the discovery surface. Multi-harness support is the point — not a single-vendor skill pack.","theCatch":"★32871 in about 37 weeks (~889 a week): judge it on the CLI/ecosystem substance, not the star count. Vs agent-skills (Addy) / mattpocock-skills / bmad-method / skillbox: those are lifecycle skills content, engineering SKILL.md packs, BMAD methodology, or a self-hosted skills library — this catch is the Vercel Labs installer/CLI + skills.sh ecosystem, not the content packs themselves. Skill quality varies by author; pair with SkillSpector-class scanning before fleet trust.","verdict":"MIT skills CLI when you need one installer across harnesses — not Addy/Matt/BMAD content packs and not Skillbox self-host; treat the star spike with caution.","addedAt":"2026-10-01","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["cli","self-host","permissive","coding-agents","skills","active","fast-stars"],"capabilities":["skills","cli","ecosystem"],"surfaces":["CLI","Self-host"],"ecosystem":["Node.js","Multi-platform"],"licenseModel":"OSS/MIT","githubStars":35525,"starsPerWeek":893,"access":"free","archived":false,"repo":{"createdAt":"2026-01-14","pushedAt":"2026-10-09","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/vercel-skills","html":"/gems/vercel-skills","markdown":"/gems/vercel-skills.md"}},{"slug":"insforge","name":"InsForge","tagline":"Apache agent-native backend with MCP self-host","category":"agents","url":"https://insforge.dev","github":"https://github.com/InsForge/InsForge","pricing":"freemium","hook":"InsForge is an Apache backend built for coding agents — Postgres, auth, storage, functions, and a model gateway that agents drive over MCP or (on cloud) CLI skills.","whatsGood":"Apache-2.0 (InsForge/InsForge). Real zero-dollar path is Docker Compose self-host from the repo (MCP server on your stack). Cloud Free exists ($0/mo with MAU/DB/storage/function caps; free projects pause after 1 week idle). Docs at docs.insforge.dev; homepage insforge.dev. ★~13,047 / F1,210 — treat as popular, not proof of ops maturity.","theCatch":"Cloud: Free is capped and pauses; Pro (~$20–25/mo) plus separate InsForge Compute and model-gateway usage. Vs Supabase: Supabase is the general Postgres+auth+storage Firebase alt; InsForge’s catch is agent-native MCP/CLI control of the same class of backend, not a better dashboard alone. Self-host still means you run Postgres and the compose stack.","verdict":"Apache agent-native backend when coding agents should own DB/auth/storage over MCP — not plain Supabase; cloud Free is capped, Compose is the unlimited OSS path.","addedAt":"2026-10-03","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["mcp","cli","self-host","free-tier","permissive","coding-agents","skills","auth","postgres","active"],"capabilities":["mcp","cli","auth"],"surfaces":["MCP","CLI","Self-host","Hosted"],"ecosystem":["Multi-platform"],"licenseModel":"Freemium","githubStars":13145,"starsPerWeek":206,"access":"free","archived":false,"repo":{"createdAt":"2025-07-29","pushedAt":"2026-10-18","license":"Apache-2.0","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/insforge","html":"/gems/insforge","markdown":"/gems/insforge.md"}},{"slug":"open-knowledge","name":"OpenKnowledge","tagline":"GPL-3.0 local markdown IDE + LLM wiki — MCP/skills for agent editing","category":"agents","url":"https://openknowledge.ai","github":"https://github.com/inkeep/open-knowledge","pricing":"open-source","hook":"OpenKnowledge is a GPL local markdown IDE and LLM wiki — WYSIWYG notes with side-by-side Claude/Codex/OpenCode agents, MCP, skills, and agentic search.","whatsGood":"GPL-3.0 (inkeep/open-knowledge). Desktop (macOS/Windows/Linux) plus web UI/CLI; private local-first path; MCP/skills/agentic search for LLM wikis and specs. Homepage openknowledge.ai with download. ★~4,373 / F289. Free path is the GPL app on your machine — no paywall required to edit local markdown.","theCatch":"License: GPL-3.0 — copyleft applies if you redistribute modifications; fine for personal/internal use, diligence for SaaS forks. Vs Obsidian-class note apps and generic MCP file tools: this catch is a WYSIWYG markdown IDE with harness-side agent editing + MCP, not a second brain plugin alone. Team sync rides git/GitHub — that is ops, not magic.","verdict":"GPL local markdown IDE when agents should edit your LLM wiki beside you — not a hosted Notion clone; respect copyleft on redistribute.","addedAt":"2026-10-03","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["mcp","self-host","local-first","copyleft","coding-agents","skills","active","young-repo"],"capabilities":["mcp"],"surfaces":["MCP","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"GPL-3.0","githubStars":4619,"starsPerWeek":233,"access":"free","archived":false,"repo":{"createdAt":"2026-06-03","pushedAt":"2026-10-18","license":"GPL-3.0","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/open-knowledge","html":"/gems/open-knowledge","markdown":"/gems/open-knowledge.md"}},{"slug":"openchatx","name":"OpenChatX","tagline":"MIT local ChatGPT agent runtime — tools, MCP aggregate, skills","category":"agents","url":"https://github.com/XiaoPuOuO/openchatx-mcp","github":"https://github.com/XiaoPuOuO/openchatx-mcp","pricing":"open-source","hook":"OpenChatX turns regular ChatGPT Chat into a local agent runtime — file/shell tools, computer control, MCP aggregation, skills, projects, and subagents over OpenAI’s documented MCP path, without burning Codex/Work agent quotas.","whatsGood":"MIT (XiaoPuOuO/openchatx-mcp). Releases/downloads on GitHub; uses official ChatGPT MCP integration (no reverse engineering claimed). Local toolbox customization; MCP registry listings. ★~250.","theCatch":"Product: you need a ChatGPT account that can connect MCP — this is not a free model seat. Safety: runs with your local user permissions; a trusted ChatGPT caller can run commands and hit connected MCP servers. Vs Claude Code / OpenCode / t3-code: those are coding-agent harnesses; OpenChatX’s catch is ChatGPT-Chat-as-local-agent-runtime. Pin a release; treat connector trust like root.","verdict":"MIT ChatGPT-local agent runtime when you want Chat tools+MCP on your machine without Codex quota — not Claude Code; budget ChatGPT access and local blast radius.","addedAt":"2026-10-04","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["mcp","self-host","permissive","coding-agents","skills","active","young-repo"],"capabilities":["mcp"],"surfaces":["MCP","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":336,"starsPerWeek":88,"access":"free","archived":false,"repo":{"createdAt":"2026-09-23","pushedAt":"2026-10-18","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/openchatx","html":"/gems/openchatx","markdown":"/gems/openchatx.md"}},{"slug":"skills-manager","name":"Skills Manager","tagline":"MIT desktop app that keeps one agent-skills library and syncs it into Claude Code, Codex, Cursor and dozens more","category":"agents","url":"https://skillsmanager.dev","github":"https://github.com/xingkongliang/skills-manager","pricing":"open-source","hook":"Skills Manager gives every SKILL.md you collect one home (~/.skills-manager) and then symlinks or copies the right ones into each coding agent, globally or per project, so you stop hand-copying folders between tools.","whatsGood":"MIT (xingkongliang/skills-manager), release v1.40.3 (2026-10-01). Tauri 2 / Rust app for macOS (`brew install --cask skills-manager`), Windows and Linux (x64 and arm64), with a CLI bundled in every installer. Import from Git repos, local folders, .zip/.skill archives or the skills.sh marketplace; presets to switch whole skill sets on per agent; upstream update checks on Git-sourced skills; diff local against upstream before updating. Optional backup and multi-device sync to a private GitHub repo. A `manage-skills` skill lets your agents drive the app instead of writing into each other's folders. ★~6k.","theCatch":"A single-maintainer project on a fast release cadence, so expect UI churn. Presets are a one-time copy, not a live sync, so a skill applied by preset will not follow later edits unless you re-apply. Installing marketplace skills in bulk is still installing other people's instructions into your agents — read them, especially ones that run scripts. GitHub sync means signing the app into GitHub. Vs cc-switch (provider switching with skills management on the side) and vercel-skills (the `npx skills` CLI): this is the dedicated GUI for people juggling many agents.","verdict":"If you run more than two coding agents and your skills folder has become a mess, this is the free fix.","addedAt":"2026-10-11","featured":false,"domain":"AI Agents","subSpecialty":"Skills","subcategory":"Skills","tags":["sdk","desktop-app","self-host","permissive","coding-agents","skills","active"],"capabilities":["skills","desktop","sync"],"surfaces":["Self-host"],"ecosystem":["Rust","Multi-platform"],"licenseModel":"OSS/MIT","githubStars":6515,"starsPerWeek":197,"access":"free","archived":false,"repo":{"createdAt":"2026-03-02","pushedAt":"2026-10-18","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/skills-manager","html":"/gems/skills-manager","markdown":"/gems/skills-manager.md"}},{"slug":"hermes-agent","name":"Hermes Agent","tagline":"MIT self-improving agent from Nous Research — skills from experience, multi-channel gateway, any model","category":"agents","url":"https://hermes-agent.nousresearch.com","github":"https://github.com/NousResearch/hermes-agent","pricing":"open-source","hook":"Hermes Agent is a self-hosted agent with a closed learning loop: it writes skills from hard tasks, improves them in use, searches past sessions, and keeps a deepening model of you — reachable from a TUI or from Telegram, Discord, Slack, WhatsApp and Signal through one gateway.","whatsGood":"MIT (NousResearch/hermes-agent), release v0.21.6 (2026-10-08). Install via the official curl/bash or PowerShell scripts; docs also cover MSIX on Windows. Bring any OpenAI-compatible endpoint (Nous Portal, OpenRouter, OpenAI, local, and more) and switch with `hermes model`. Full TUI with slash commands and streaming tool output; messaging channels share one gateway process with cross-platform conversation continuity. ★~253k.","theCatch":"A full personal/coding agent surface, not a drop-in Claude Code plugin — you run the gateway and own model keys, channel tokens and the memory/skill store it writes. Exact-pinned Python deps and a 3.14-oriented install path mean supply-chain and upgrade care; follow their install docs rather than improvising. Multi-channel access widens the security surface the same way OpenClaw does. Vs openclaw (freemium multi-channel assistant) and claude-code (paid Anthropic terminal agent): Hermes is the MIT self-improving host you operate yourself. oh-my-hermes is niche plugin tooling for this host, not a substitute. Stars have grown extremely fast (about 3,940 a week since the repo opened in July 2025), so judge it on a trial run, not the count.","verdict":"The open-source agent with a real learning loop — run it if you want skills and memory you own, not another rented chat UI.","addedAt":"2026-10-12","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["tui","self-host","permissive","skills","active","fast-stars"],"capabilities":[],"surfaces":["Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":255005,"starsPerWeek":3927,"access":"free","archived":false,"repo":{"createdAt":"2025-07-22","pushedAt":"2026-10-19","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/hermes-agent","html":"/gems/hermes-agent","markdown":"/gems/hermes-agent.md"}},{"slug":"trueforge","name":"TrueForge","tagline":"MIT open-source agent harness — MCP, skills, subagents, approvals, local SQLite or hosted Postgres","category":"agents","url":"https://trueforge.dev","github":"https://github.com/truefoundry/trueforge","pricing":"open-source","hook":"TrueForge is the runtime layer that turns an LLM endpoint into a working agent: tool loop, MCP servers, git-backed skills, subagents, approval gates and session state that survives a restart.","whatsGood":"MIT (truefoundry/trueforge), npm `@truefoundry/trueforge` 0.178.0 (2026-10-09). Quickstart with `npx @truefoundry/trueforge`; Node.js ≥ 22.14. Local mode is one process plus SQLite; hosted mode adds Postgres and Redis via Docker Compose, Helm or Railway. Speaks OpenAI-compatible APIs including Ollama and vLLM. MCP with header auth or OAuth, including in-chat authorization. ★~6.2k.","theCatch":"It is a harness you integrate, not a finished coding IDE — you still bring models, sandboxes for code execution, and the product UI around it. Requires a current Node (22.14+). Built by TrueFoundry; expect the OSS path to sit next to their commercial platform messaging. Vs langchain / crewai (framework kits) and hermes-agent (batteries-included personal agent): TrueForge is the embeddable runtime when you are shipping your own agent product. Stars have climbed fast for a repo opened in July 2026 (about 500 a week), so don’t read the count as proof of maturity.","verdict":"The MIT harness to stop re-implementing agent loops — start local with SQLite, scale out when you need Postgres.","addedAt":"2026-10-12","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["mcp","self-host","permissive","skills","postgres","git","active","young-repo"],"capabilities":["mcp"],"surfaces":["MCP","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":6293,"starsPerWeek":497,"access":"free","archived":false,"repo":{"createdAt":"2026-07-23","pushedAt":"2026-10-19","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/trueforge","html":"/gems/trueforge","markdown":"/gems/trueforge.md"}},{"slug":"fabric","name":"Fabric","tagline":"MIT CLI that runs a library of reusable prompt patterns","category":"agents","url":"https://github.com/danielmiessler/Fabric","github":"https://github.com/danielmiessler/Fabric","pricing":"open-source","hook":"Fabric is a Go command-line tool that runs named prompts (patterns) over whatever you pipe in, such as a transcript, an article or a log, so a task like extract_wisdom or summarize becomes one shell command instead of a pasted prompt.","whatsGood":"MIT (danielmiessler/Fabric), very active (release v1.4.523, 2026-10-16). About 260 patterns ship in data/patterns, and you can add your own as plain markdown. It works with many providers, including Ollama for local models and any OpenAI-compatible endpoint, and lets you pick a model per pattern. fabric --serve exposes the same patterns as a REST API with Swagger docs. Installs with brew install fabric-ai, winget, go install or Docker. ★~44.3k.","theCatch":"It is a prompt runner, not an agent: one pattern in, one completion out, with no tools or loop. Pattern quality varies, and many target writing, research or personal reflection rather than code. You bring your own provider key and pay its token costs. The quick-start installer is a curl | bash script, so read it first or use brew or go install. The star count has climbed quickly (about 300 a week since Jan 2024), so weigh it by the patterns you actually use, not the number.","verdict":"The cleanest way to turn your best prompts into shell commands — keep the few patterns that fit and write your own.","addedAt":"2026-10-16","featured":false,"domain":"AI Agents","subSpecialty":"Agents","subcategory":"Skills","tags":["cli","sdk","self-host","permissive","skills","active"],"capabilities":["cli"],"surfaces":["CLI","Self-host"],"ecosystem":["Multi-platform"],"licenseModel":"OSS/MIT","githubStars":44348,"starsPerWeek":304,"access":"free","archived":false,"repo":{"createdAt":"2024-01-03","pushedAt":"2026-10-18","license":"MIT","archived":false,"checkedAt":"2026-10-19"},"links":{"self":"/api/gems/fabric","html":"/gems/fabric","markdown":"/gems/fabric.md"}}],"meta":{"total":25,"count":25,"offset":0,"limit":null,"sort":"curated","sorts":["curated","catalog","new","stars","trending","name"],"filters":{"subcategory":"skills"},"next":null,"categories":["agents","nextjs","python","shopify","databases","devops","design","observability","rust","payments","comms","notifications","libraries"],"tags":["mcp","cli","tui","api","sdk","desktop-app","web-ui","editor-plugin","self-host","local-first","free-tier","paid-only","paid-led","permissive","copyleft","source-available","license-unclear","coding-agents","local-llm","rag","memory","evals","browser-automation","scraping","sandbox","skills","voice","security","auth","payments","realtime","postgres","vector","kubernetes","containers","observability","testing","workflows","graphics-3d","git","active","stale","archived","young-repo","fast-stars"]}}