Browse curated Claude Code Skills, MCP servers, Subagents, Hooks, CLAUDE.md configs, and more. The open directory for everything the community has built to extend Claude.
GitHub's official MCP server for repos, issues, PRs, and Actions
MCPs
The official Model Context Protocol server from GitHub. Gives Claude direct access to repositories, issues, pull requests, code scanning, and GitHub Actions through natural language.
Browser automation for Claude via Playwright's accessibility tree
MCPs
Microsoft's official MCP server that lets Claude drive a real browser using structured accessibility snapshots instead of screenshots — fast, deterministic web automation without vision models.
Up-to-date, version-specific library docs injected into Claude's context
MCPs
An MCP server that fetches current, version-specific documentation and code examples for thousands of libraries — ending hallucinated APIs from stale training data.
Connect Claude to your Supabase projects — database, auth, storage, and more
MCPs
The official Supabase MCP server — lets Claude query your database, manage tables, run migrations, and inspect your project configuration through natural language.
Create distinctive, production-grade frontend interfaces with high design quality
Skills
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Suite of tools for creating elaborate, multi-component claude
Skills
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.
Toolkit for interacting with and testing local web applications using Playwright
Skills
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.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact...
Skills
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).
CLI to browse and install hundreds of agents, commands, hooks, and MCPs
Plugins
A popular open-source CLI and web catalog (aitmpl.com) for configuring Claude Code — install agents, commands, settings, hooks, and MCPs from a large community collection, plus analytics dashboards.
Official guide to installing, building, and publishing plugins
Plugins
Anthropic's official plugin documentation — plugin anatomy (commands, agents, skills, hooks, MCP servers), marketplace management, and how to build and distribute your own.
The community wing of Anthropic's plugin ecosystem
Plugins
Anthropic's community plugin marketplace — a broader, screened collection of community-built Claude Code plugins that complements the stricter official directory.
Real CLAUDE.md files collected from public projects
CLAUDE.md
A collection of real-world CLAUDE.md files gathered from public repositories — see how different teams structure project context, commands, and conventions before writing your own.
Official reference for CLAUDE.md memory files, imports, and precedence
CLAUDE.md
Anthropic's official documentation on Claude Code memory — enterprise, project, and user CLAUDE.md locations, the @import syntax, lookup precedence, and quick-add shortcuts.
Anthropic's engineering guide to writing effective CLAUDE.md files
CLAUDE.md
The canonical article on CLAUDE.md from Anthropic's engineering team — what to include (commands, style, workflows), where files can live, and how to tune them for agentic coding.
Hundreds of framework-specific rule files, easily adapted to CLAUDE.md
Rules
The largest collection of .cursorrules files — framework- and stack-specific coding rules (Next.js, React Native, Python, Go, and hundreds more) whose content translates directly into CLAUDE.md instructions.
Battle-tested rules and workflows for Claude Code and Cursor
Rules
Peter Steinberger's collection of reusable agent rules — commit conventions, code-quality checks, debugging workflows, and language-specific guidance that work as both Cursor rules and CLAUDE.md sections.
The open standard for giving coding agents project instructions
Rules
AGENTS.md is an open, cross-tool format for agent instructions — one markdown file that coding agents (including Claude Code) read for build steps, conventions, and project rules.
A curated collection of community output styles worth stealing
Styles
A curated list of community-made Claude Code output styles — from pragmatic (code-first, minimal prose) to playful — each linked with a description of what it changes.
CLI tool and template gallery for Claude Code output styles
Styles
A CLI and template gallery for customizing Claude Code output styles — browse pre-built styles and install them with one command instead of writing style files by hand.
Official guide to creating and switching Claude Code output styles
Styles
Anthropic's official documentation for output styles — how they modify Claude Code's system prompt, the built-in styles, and how to create custom ones with /output-style:new.
A massive crowdsourced library of task prompts, usable from the CLI
Prompts
Fabric is an open-source framework with hundreds of crowdsourced prompt 'patterns' — extract_wisdom, summarize, analyze_claims, write_essay — each a refined, reusable system prompt for a specific task.
Anthropic's official 9-chapter interactive course on prompting Claude
Prompts
Anthropic's official interactive tutorial — nine chapters with exercises that take you from basic prompt structure to complex multi-step prompts, tool use, and hallucination avoidance.
Anthropic's official library of optimized prompts for dozens of tasks
Prompts
The official prompt library from Anthropic — dozens of tested prompt templates for business and personal tasks, each with system prompt and example, ready to copy into Claude or the API.
Professional slash commands that save hours per week on routine dev work
Commands
A curated command framework for Claude Code — /cleanproject, /commit, /review, /security-scan, /refactor and two dozen more, designed around real engineering workflows rather than demos.
The community's master list of slash commands, workflows, and tooling
Commands
The canonical awesome-list for the Claude Code ecosystem — curated slash commands, CLAUDE.md files, hooks, workflows, and tooling, actively maintained with community submissions.
100+ professional slash commands for dev, testing, and project workflows
Commands
A large suite of ready-made slash commands for Claude Code — code review, feature creation, security audit, test generation, dependency updates, release workflows, and much more.
The official reference for every hook event, schema, and exit-code behavior
Hooks
Anthropic's official hooks documentation — the authoritative reference for hook events, JSON input/output schemas, matchers, exit-code semantics, and security considerations.
Learn every Claude Code hook lifecycle event with working examples
Hooks
The definitive hands-on repo for Claude Code hooks — working examples for every lifecycle event (PreToolUse, PostToolUse, Notification, Stop, and more) with UV single-file Python scripts.
A compact, practical set of custom subagents for everyday dev work
Subagents
An early and influential set of custom Claude Code subagents — practical roles like code refactorer, frontend designer, content writer, and PRD writer, kept simple enough to read and adapt in minutes.
A widely-used collection of focused, single-responsibility subagents
Subagents
One of the most popular subagent collections for Claude Code — dozens of production-oriented agents covering languages, frameworks, DevOps, security review, and architecture, designed for automatic delegation.
The official collection of reference MCP server implementations
MCPs
The canonical repository of reference Model Context Protocol servers — Filesystem, Fetch, Git, Memory, Time, and more — maintained by the MCP project itself, plus a huge index of community servers.
Up-to-date, version-specific library docs injected into Claude's context
MCPs
An MCP server that fetches current, version-specific documentation and code examples for thousands of libraries — ending hallucinated APIs from stale training data.
Browser automation for Claude via Playwright's accessibility tree
MCPs
Microsoft's official MCP server that lets Claude drive a real browser using structured accessibility snapshots instead of screenshots — fast, deterministic web automation without vision models.
Toolkit for interacting with and testing local web applications using Playwright
Skills
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.
Suite of tools for creating elaborate, multi-component claude
Skills
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.
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.
Knowledge and utilities for creating animated GIFs optimized for Slack
Skills
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."
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
A set of resources to help me write all kinds of internal communications, using the formats that...
Skills
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
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.