Skip to content
←Back to Skills

AGENT SKILL

Official & CollectionsFeatured

A curated index of 1000+ skills, plus one genuinely unique connect-apps plugin

ComposioHQ/awesome-claude-skills

A list maintained by Composio at 75k stars with an Apache-2.0 badge in the README. About 31 first-party skill directories physically exist here while the index references 864 SKILL.md files, and most of the difference is links out to external repositories. Coverage explicitly extends beyond Claude.ai and Claude Code to Codex, Cursor, Gemini CLI and Antigravity.

Editor's takeThere is no one-liner that installs this repo; use it as a discovery layer. A list answers what exists, not what is worth running. The part you cannot get elsewhere is connect-apps-plugin: a single MCP endpoint to 1000+ integrations with authentication, team-level ACLs and audit logs, which is exactly the governance problem enterprises hit when agents touch SaaS.
claude --plugin-dir ./connect-apps-plugin
Any agent
Agent SkillsAwesome ListCurationMCP
ComposioHQ/awesome-claude-skills75.4k8.7kPythonComposioHQ3 min read

What it is: a list, not an installable bundle

Composio's awesome-claude-skills is a curated index of "1000+ production ready and practical Claude Skills and Plugins", at 75,385 stars / 8,735 forks with an Apache-2.0 badge in the README. Coverage explicitly extends beyond Claude.ai and Claude Code to coding agents including Codex, Cursor, Gemini CLI and Antigravity.

Set expectations first: there is no one-liner that installs this whole repo. About 31 first-party skill directories physically exist here, while the index references 864 SKILL.md files — most of the difference is links out to external repositories. So the correct use is as a discovery layer: find candidates here, then go read each project's README, licence and maintenance state. That gap is precisely why this site exists — a list answers "what exists", not "what is worth running".

The first-party skills are genuinely usable

The bundled skills are not filler. Several groups are worth reading on their own:

AreaDirectories
Documents & designdocument-skills, canvas-design, theme-factory, brand-guidelines, artifacts-builder
Engineeringmcp-builder, webapp-testing, changelog-generator, skill-creator, template-skill
Growth & marketingcompetitive-ads-extractor, twitter-algorithm-optimizer, lead-research-assistant, content-research-writer, domain-name-brainstormer
Everyday opsfile-organizer, invoice-organizer, meeting-insights-analyzer, internal-comms, tailored-resume-generator, image-enhancer, video-downloader

Note that skill-creator and template-skill overlap with same-named skills in Anthropic's official repo. That is not a plagiarism story, it is the honest state of the ecosystem: the handful of foundational capabilities have already been reimplemented several times over. Pick whichever one is actively maintained.

The genuinely unique part: the connect-apps plugin

The list is replaceable. The connect-apps-plugin shipped alongside it is the thing you cannot get elsewhere in this repo. Its argument: skills tell an agent how to work, but acting for real requires tool access. connect-apps exposes a single MCP endpoint over the Composio MCP Gateway to 1,000+ integrations, with built-in authentication, team-based access controls and audit logs.

# Let Claude actually send email / open issues / post to Slack
claude --plugin-dir ./connect-apps-plugin
/connect-apps:setup

The value is not "connects to many apps" — everyone in the MCP ecosystem claims that — it is auth and permission governance. The blocker for agents touching SaaS inside a company was never the protocol; it is whose token it is, what it may do, and whether you can audit it afterwards. ACLs plus audit logs map straight onto that.

The low-friction way to use it

  • Install connect-apps first if your agent needs real side effects, then pick domain skills;
  • Treat the index as keyword scanning rather than clicking through — there is no human quality tier among the 864 SKILL.md entries, and star counts are not in the list;
  • For entries pointing at external repos, verify the licence before shipping. The first-party directories are Apache-2.0; the indexed third parties each differ.

Related skills

Developmentmattpocock/skillsFeatured

The 38 skills Matt Pocock uses every day for real engineering

Editor's takeSells parts, not a process: 38 SKILL.md behind a strict user/model-invoked contract, a SCOPE.md admission bar and a shared GLOSSARY.md; the spec-to-tickets-to-implement-spec pipeline is the most complete agentic engineering loop in this channel.

Daily-working set of the Total TypeScript author: 38 SKILL.md files (engineering 20, productivity 7, misc 4 frozen, in-progress 7) behind a user-invoked/model-invoked contract, a SCOPE.md admission bar and a shared GLOSSARY.md; installs as a Claude Code, Codex, Copilot or Gemini plugin, or an editable skills.sh copy.

Claude CodeCodexGemini CLI+2
claude plugin install mattpocock-skills@claude-plugins-official
Shellmattpocock289.9k
The 38 skills Matt Pocock uses every day for real engineering
Developmentobra/superpowersFeatured

Fifteen skills that give a coding agent a full development process

Editor's takeIts premise is that models lack process discipline, not coding ability. The single best idea to steal is 'Rulings, not stalls': decide by default, and stop for a human only when an action is irreversible, touches a security-sensitive surface, leaks outside the worktree, or the plan is already too broken to continue.

v6.4.1 (2026-09-18), MIT, 289k stars — the largest single skill repository of its kind. It chains brainstorming, spec writing, git-worktree isolation, planning, subagent execution, red-green TDD, two-way code review and verification-before-completion into one trunk workflow, and the README lists 16+ harnesses: Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Kimi Code, Devin CLI and more.

Claude CodeCodexCursor
/plugin install superpowers@claude-plugins-official
Shellobra289.2k
Fifteen skills that give a coding agent a full development process
Official & Collectionsanthropics/skillsFeatured

The official repo from the format's author: 19 skills plus spec and template

Editor's takeIf you want to know how a SKILL.md is actually supposed to be written, read this instead of any second-hand tutorial. Two things to know first: docx, pdf, pptx and xlsx are source-available rather than open source (the other 15 are Apache-2.0), and the repo carries its own disclaimer — these skills are demos, so test them in your environment before trusting them with anything critical.

Anthropic's own implementation, 177k stars: 19 skills under ./skills plus ./spec (the Agent Skills specification, now at agentskills.io) and ./template as a scaffold. Its definition of a skill is folders of instructions, scripts and resources loaded dynamically, and progressive disclosure comes straight from here.

Claude Code
/plugin marketplace add anthropics/skills
Pythonanthropics177.3k
The official repo from the format's author: 19 skills plus spec and template
Design & FrontendLeonxlnx/taste-skillFeatured

Taste Skill: 13 anti-slop frontend skills that turn AI tells into countable rules

Editor's takeThe lesson worth stealing is rules expressed as countable mechanical tests: eyebrow count ≤ ceil(sections/3), bento cells equal to content items, zero em-dashes on the page, palette families rotated across projects. Each one aims straight at the model repeating itself instead of stopping at an adjective. The repo is equally honest about its edges: v2 self-declares experimental and is still moving, §13 explicitly excludes dashboards, data tables, multi-step wizards, code editors and native mobile, and the only test in the repo guards the source-invocation semantics of the skill.sh shell helper rather than the design rules.

One MIT repo holding 13 skills: ten that output code and three that output reference images only, all installed into Claude Code / Codex / Cursor with a single npx skills add. The default design-taste-frontend v2 (experimental) is a 1,228-line SKILL.md: first the model must emit a one-line "design read", then it sets three dials (DESIGN_VARIANCE / MOTION_INTENSITY / VISUAL_DENSITY), then it implements against 14 chapters of hard rules - install the official package for corporate briefs, label aesthetic borrowings in comments, zero em-dashes anywhere on the page, eyebrow quota computed from section count, bento cells equal to content items, and finally a 50-plus box pre-flight check. The repo also ships research/laziness, a literature directory using controlled studies to explain why models cut output short.

Claude CodeCodexCursor
npx skills add https://github.com/Leonxlnx/taste-skill
JavaScriptLeonxlnx94.8k
Taste Skill: 13 anti-slop frontend skills that turn AI tells into countable rules

As an Amazon Associate, we earn from qualifying purchases.