awesome-claude-skills

A curated list of more than a thousand Claude Skills and plugins, with a README that doubles as a primer on the skill format, how skills load, and how they differ from tools and MCP servers.

Awesome Claude Skills calls itself a comprehensive and curated list of 1000 plus production ready and practical Claude Skills and plugins, for use on Claude.ai and Claude Code as well as coding agents like Codex, Cursor, Gemini CLI, and Antigravity. A sponsoring section promotes the Composio MCP Gateway, a single MCP endpoint for 1,000 plus integrations with built in authentication, team based access controls, audit logs, and production ready reliability, plus a connect apps plugin that lets Claude send emails, create issues, and post to Slack.

The README doubles as documentation for the format. A Claude Skill is a reusable instruction package that teaches an AI agent how to handle a class of tasks. Each skill is a folder containing a SKILL.md file with YAML frontmatter for name and description and Markdown instructions, optionally bundled with scripts, references, and assets. Anthropic introduced the format in October 2025 and released it as an open standard in December 2025, and it is now supported across Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI, Antigravity, and Windsurf.

The loading model explains why a single agent can host hundreds of skills. Skills load progressively: at session start the agent sees only each skill's name and description, roughly 100 tokens per skill. The full SKILL.md body, typically under 5,000 tokens, loads only when the agent decides the skill is relevant to the current task, and auxiliary files in scripts and references load on demand. That keeps the context window from bloating.

A short section draws the boundaries. Skills are not MCP servers and not tools. MCP defines how an agent connects to external systems, covering auth, transport, and tool discovery. Tools are the individual functions an agent invokes. Skills define the workflow: what to do, in what order, with what guardrails, once the agent has the connections and tools it needs. In production the three layers run together.

The list itself is organized by category. Document processing covers docx, pdf, pptx, and xlsx skills, plus a markdown to EPUB converter. Development and code tools include aws-skills, a changelog generator, and Chrome Relay. Data and analysis brings a CSV summarizer, deep research, and a postgres skill. Business, marketing, communication and writing, creative and media, productivity, and collaboration sections round it out, including git-pushing and google workspace skills.

• Source 1 · Project repository
• Source 2 · README