Agent skills

• Google Workspace CLIApache-2.0 first-party gws CLI — Drive, Gmail, Calendar, agent skills

  Free / OSS · Apache-2.0 · 31.7k GitHub stars

  VerdictApache-2.0 Workspace CLI. First-party org tooling for agents; not a Google support SLA.

  CatchFirst-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.

• LibreChatMIT Agents/MCP chat UI — OpenAI-compatible, self-host

  Free / OSS · OSS/MIT · 46k GitHub stars

  VerdictMIT Agents/MCP chat UI. Self-host orchestration vs Open WebUI/AnythingLLM; BYO models.

  CatchVs Open WebUI / AnythingLLM (local RAG chat UIs): LibreChat leans hard into Agents/MCP/skills orchestration and multi-provider routing, not only RAG chat. You own auth, model keys, vector/DB ops, and upgrade discipline — the OSS UI is free; the models and infra are not.

• Security Audit SkillMIT coding-agent skill for multi-phase security audits

  Free / OSS · OSS/MIT · 31.2k GitHub stars

  VerdictMIT agent security-audit skill. Phased findings vs mcp-security-audit; not a SaaS scanner.

  CatchSkill only — not a standalone SaaS scanner. Distinct from mcp-security-audit (awesome-copilot skill for .mcp.json / MCP config audits) and from OWASP ASI checklist skills: this is Cloudflare’s multi-phase code/security audit skill for a coding-agent host. You still need the agent runtime and any scanners the skill shells out to.

• ECCMIT agent ecosystem / coordination surface

  Free / OSS · OSS/MIT · 283k GitHub stars

  VerdictMIT agent coordination ecosystem. Skills+memory+security on top of host agents — not a host itself.

  CatchStill depends on host agents (Claude Code / Codex / Cursor / etc.) — ECC coordinates and tunes the harness; it is not a replacement coding agent. Vs OpenSpec (spec-driven change tooling) and Thurbox (tmux multi-agent TUI): ECC is the skills/memory/security ecosystem pack, not a spec framework and not a pane orchestrator.

• oh-my-hermesMIT Hermes-agent niche tooling — memory & workflows

  Free / OSS · OSS/MIT · 3.4k GitHub stars

  VerdictMIT Hermes-agent tooling. Niche, not a multi-host skill pack.

  CatchHermes-specific — not a generic Claude Code / Codex skill pack. Young surface; expect Hermes Agent as the host and follow upstream Hermes breaking changes. Vs ECC (multi-host ecosystem) and security-audit-skill (Cloudflare audit skill): oh-my-hermes is niche Hermes tooling, not a cross-harness coordination layer or a security scanner.

• SuperpowersComposable agent skills that force brainstorm → plan → TDD → subagent review

  Free / OSS · OSS/MIT · 302k GitHub stars

  VerdictMIT agent methodology. Install when your agent skips specs and tests; not a replacement for the harness itself.

  CatchYou 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.

• Agent Skills (Addy Osmani)Production lifecycle skills — /spec /plan /build /test /review /ship

  Free / OSS · OSS/MIT · 108k GitHub stars

  VerdictMIT production skill pack. Reach for it when you want explicit /spec→/ship gates across many harnesses.

  CatchPer-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.

• OpenVikingAGPL self-evolving context database for memory, RAG, and skills

  Free / OSS · AGPL-3.0 · 40.3k GitHub stars

  VerdictAGPL-3.0 self-evolving context DB. Broad memory/RAG/skills surface; network copyleft is a deployment decision, not a footnote.

  CatchAGPL-3.0 is strong copyleft, including the network-copyleft boundary when you modify OpenViking and offer it as a service. Get legal review before exposing a modified deployment over a network. Vs Mem0, Graphiti, and Letta: OpenViking is the context database spanning memory/RAG/skills, not simply a memory API, graph memory layer, or agent runtime.

• ArchifyMIT agent skill that renders architecture and workflow diagrams as self-contained HTML

  Free / OSS · OSS/MIT · 85.5k GitHub stars

  VerdictMIT agent diagram skill. Handy portable HTML for architecture/workflow/sequence views; validate generated relationships against the code.

  CatchVs 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.

• FlueAstro TypeScript harness for autonomous sandbox agents

  Free / OSS · Apache-2.0 · 8.5k GitHub stars

  VerdictApache-2.0 Astro agent harness. Use when you want programmable TypeScript agents with real sandboxes; bring your own models and host.

  CatchVs AgentBox and Octop: Flue is a TypeScript framework for authoring agent harnesses, not a multi-user agent platform or a generic sandbox/VM launcher. You still bring models, credentials, and operational judgment; a dead flue.dev marketing domain is not required — the GitHub repo is the source of truth.

• CavemanViral skill and proxy that forces coding agents to spend fewer tokens

  Free / OSS · Apache-2.0 · 114k GitHub stars

  VerdictMIT skill surface with BSL engine bits. Use to cut coding-agent token spend; read the BSL boundary before productizing the runtime.

  CatchEngine-linked runtime directories (engine/, proxy/, rewriter/, and related) are Business Source License 1.1, not MIT — see LICENSING.md / LICENSE.BSL before embedding or offering a hosted Caveman runtime. Vs LiteLLM: Caveman is output/style compression for agent hosts, not a multi-provider model gateway. Terse output can hide nuance; keep quality checks on hard tasks.

• Stitch SkillsGoogle Labs agent skills and plugins for the Stitch design MCP

  Free / OSS · Apache-2.0 · 8.5k GitHub stars

  VerdictApache-2.0 Stitch-oriented agent skills. Use when coding agents should drive Google Stitch design/build flows.

  CatchVs 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.

• SkillboxSelf-hosted versioned skills library with MCP and scoped clients

  Free / OSS · OSS/MIT · 272 GitHub stars

  VerdictMIT self-hosted skills library. Use when multiple agents need a versioned, scoped skill source you control.

  CatchVs 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.

• HumanizerAgent skill that rewrites AI-sounding prose without changing the meaning

  Free / OSS · OSS/MIT · 58.2k GitHub stars

  VerdictMIT Agent Skills pack for de-AI prose. Reach for /humanizer when drafts read like a model wrote them.

  CatchVs 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.

• Codex-XCodex-specific desktop and CLI workspace for visual configuration and MCP skills

  Free / OSS · OSS/MIT · 4.2k GitHub stars

  VerdictMIT Codex desktop/CLI companion. Handy for visual MCP and skills configuration; audit auth, relay endpoints, and unrestricted templates before trusting it.

  CatchVs T3 Code: Codex-X is Codex-specific visual configuration plus MCP/skills, not a broad remote coding environment or an independent coding model. It handles `auth.json`, supports third-party relays, and allows unrestricted prompt templates — review where credentials go, which endpoint receives requests, and what instructions can execute before using a release. Treat relays as a trust decision, not a convenience toggle.

• OpenHumanGPL-3 local-first agent orchestrator with memory trees and MCP

  Free / OSS · Freemium · 42.2k GitHub stars

  VerdictGPL-3 local-first agent OS with real memory UX. Worth a look for personal orchestration; assume beta edges and price the subscription defaults honestly.

  CatchVs Pi, Claude Code, OpenClaw, and OKF/ai-memory: OpenHuman is the TinyHumans desktop orchestrator + memory product, not a coding-agent CLI harness, Anthropic's CLI, a messaging agent, or a zero-LLM git memory wiki. README marks Early Beta and managed web search / model routing / media tools ride an OpenHuman subscription by default — treat the SaaS path as freemium, not "free forever," even though the repo is GPL-3 and BYOK/local modes exist. GPL-3 copyleft applies to modifications you distribute.

• book-to-skillMIT converter from books/docs into cross-agent SKILL.md packs

  Free / OSS · OSS/MIT · 35.3k GitHub stars

  VerdictMIT book→skill converter. Excellent for private grounded skills; keep copyrighted sources offline and private.

  CatchVs Skillbox and Claude Code Templates: this generates content skills from documents, not a self-hosted skills registry/MCP plane and not a catalog of Claude Code agents/hooks/MCPs. Do not redistribute generated skills of copyrighted books — the README is explicit that third-party book skills should stay private; the tool does not grant you redistribution rights. Quality tracks your extractors (docling for technical PDFs) and the host's skill discovery rules.

• video-useVideo-editing skill stack for coding agents

  Free / OSS · OSS/MIT · 29.3k GitHub stars

  VerdictMIT 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.

  CatchVs 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.

• AI-Infra-GuardRed-team platform for agent, MCP, and skill infrastructure

  Free / OSS · Apache-2.0 · 6.9k GitHub stars

  VerdictApache-2.0 red-team platform for agent infrastructure. Worth running in a disposable, keyed environment; ship the attribution and scope every model credential.

  CatchVs Promptfoo and DeepEval: AI-Infra-Guard is an AI-infrastructure red-team platform, not only an eval runner; vs generic SAST, it understands agent/MCP/skill attack surfaces. Preserve the mandatory attribution — “Based on Tencent Zhuque Lab AI-Infra-Guard” — with the repository link in your deployment and derivative notices. Some tools also require an LLM_API_KEY, so a self-hosted scanner can still carry provider cost and credential risk.

• ImpeccableApache design language/skills that make AI harnesses better at UI

  Free / OSS · Apache-2.0 · 82.8k GitHub stars

  VerdictApache 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.

  CatchVs 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.

• DeerFlowMIT long-horizon SuperAgent harness — sandboxes, memory, skills, gateway

  Free / OSS · OSS/MIT · 84.1k GitHub stars

  VerdictMIT SuperAgent harness when you want sandboxes + skills + gateway in one OSS tree and will bring models plus Docker headroom.

  CatchVs OpenHands, LangGraph, and Mastra: DeerFlow is a full SuperAgent product harness with sandboxes/memory/gateway, not an open coding agent alone, a graph orchestration library, or a TypeScript workflow framework. BYO model API keys; Docker sizing is resource-heavy (multi-vCPU/GB guidance); star velocity is extreme (~83k).

• antislopMIT skill/rules that filter generic AI UI and copy — not a style guide

  Free / OSS · OSS/MIT · 6.5k GitHub stars

  VerdictMIT 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.

  CatchVs 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.

• unlazyMIT anti-laziness Depth Tree skill — gates, evidence, reverify

  Free / OSS · OSS/MIT · 4k GitHub stars

  VerdictMIT Depth Tree / gates skill when agents declare done without evidence; skip if you only needed a shorter system prompt.

  CatchVs 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.

• CC SwitchMIT desktop All-in-One manager for Claude Code, Codex, OpenCode, and peers

  Free / OSS · OSS/MIT · 146k GitHub stars

  VerdictMIT desktop switchboard when you juggle many coding-agent configs and MCP/skills; skip if you live in one harness with one provider.

  CatchVs 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.

• SkillSpectorApache NVIDIA scanner for agent skills before you install them

  Free / OSS · Apache-2.0 · 20.5k GitHub stars

  VerdictApache skill security gate when your agents install third-party skills — run it before the skill runs you.

  CatchVs Semgrep/Trivy-class general SAST: this is skill/MCP-skill oriented, not a whole-repo AppSec suite. Scanner signal ≠ proof a skill is safe forever — still review permissions and network egress; NVIDIA catalog signing is a separate trust path from running the OSS scanner alone.

• Qwen CodeApache-2.0 multi-surface coding agent (Qwen lineage)

  Free / OSS · Apache-2.0 · 28.6k GitHub stars

  VerdictApache-2.0 multi-surface coding agent when Qwen-lineage open models + Skills/Teams/MCP beat a closed product CLI.

  CatchVs Claude Code: paid product CLI. Vs OpenCode / ZCode / fx: other OSS coding agents — Qwen Code is the Qwen-lineage multi-surface agent with open models+framework, not a tiny Zig binary or Earendil harness fork.

• Claude for Financial ServicesApache-2.0 finance reference agents/skills (Anthropic)

  Free / OSS · Apache-2.0 · 40.3k GitHub stars

  VerdictApache-2.0 Anthropic finance agent pack when IB/ER/PE workflows need first-party skills — not general knowledge-work plugins; paid host likely.

  CatchVs 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.

• Matt Pocock SkillsMIT composable SKILL.md pack for real engineering — not vibe coding

  Free / OSS · OSS/MIT · 296k GitHub stars

  VerdictMIT real-engineering skill pack when agents need grilling, TDD, and deep-module habits — rank the workflows, not the ★ counter.

  CatchStar 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.

• PonytailMIT “laziest senior” skill — measured LOC/token/cost cuts, not vibes

  Free / OSS · OSS/MIT · 167k GitHub stars

  VerdictMIT laziest-senior skill when agents over-build; trust the published benches over the ★ count — waitlist is tease, not tollbooth.

  CatchSame 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.

• SkillOptMIT skills optimizer — trains skill.md as params for frozen agents

  Free / OSS · OSS/MIT · 18.5k GitHub stars

  VerdictMIT skill trainer when frozen agents need evolved skill.md — not another hand-pack; ignore the star spike.

  Catch★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.

More with this tag (14)

• Agent Toolkit for AWS — Apache-2.0 Agents/MCP toolkit — plugins, skills, AWS CLI MCP proxy
• BMAD Method — MIT agent skills method — npm bmad-method, not proprietary
• Skills (Vercel Labs) — MIT open agent-skills CLI — npx skills, skills.sh ecosystem
• HOL Guard — Apache local antivirus for agents — MCP, skills, shell, packages
• InsForge — Apache agent-native backend with MCP self-host
• OpenKnowledge — GPL-3.0 local markdown IDE + LLM wiki — MCP/skills for agent editing
• OpenChatX — MIT local ChatGPT agent runtime — tools, MCP aggregate, skills
• Diagram Design — MIT agent skill for editorial HTML/SVG diagrams — 40+ layout types, brand-matched, no server
• eve — Apache-2.0 filesystem-first framework for durable AI agents — from Vercel
• PPT Master — MIT agent skill that turns documents into natively editable PowerPoint decks — real shapes, charts and slide masters
• Skills Manager — MIT desktop app that keeps one agent-skills library and syncs it into Claude Code, Codex, Cursor and dozens more
• Hermes Agent — MIT self-improving agent from Nous Research — skills from experience, multi-channel gateway, any model
• TrueForge — MIT open-source agent harness — MCP, skills, subagents, approvals, local SQLite or hosted Postgres
• Fabric — MIT CLI that runs a library of reusable prompt patterns