Claude Skills
Browsing Claude Skills only. Show all platforms →
The skills directory links to third-party GitHub repositories. Some skills may contain untested or potentially harmful code. We take no responsibility for third-party content. We strongly recommend using the Claude Code security review skill to audit any code before installing it on your system.
Top Claude Skills
The highest-starred Claude Skills in the directory.
claude-mem
SkillA Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
oh-my-openagent
Skillomo; the best agent harness - previously oh-my-opencode
Understand-Anything
SkillGraphs that teach > graphs that impress. Turn any code, or knowledge base (Karpathy LLM wiki), into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
agents
SkillIntelligent automation and multi-agent orchestration for Claude Code
scientific-agent-skills
SkillA set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.
awesome-agent-skills
SkillA curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
How OpenClaw Works
Six components that power every OpenClaw agent
Gateway
The routing layer that receives requests, authenticates callers, and dispatches to the right agent.
Brain
LLM orchestration, reasoning chains, and decision-making logic that powers every OpenClaw agent.
Memory
Persistent context, vector stores, and conversation history that give agents long-term recall.
Skills
Modular capabilities agents can learn — from web search and code execution to API calls and file I/O.
Heartbeat
Health monitoring, scheduling, and lifecycle management that keeps agents running reliably.
Workforce
Design an entire AI workforce with defined roles, handoffs, and shared context.
Recent Updates
Latest discoveries and project additions
Who Is This For?
Whether you build, research, or deploy — there’s something here for you
Developers
Build custom agents with OpenClaw's modular architecture. Thousands of skills, plugins, and integrations to compose.
Users
Deploy pre-built agents for productivity, research, coding, and daily tasks — no programming required.
Enterprises
Run agents on your own infrastructure with full data control, SSO, audit logs, and compliance features.
Contributors
Join 5,000+ contributors shaping the OpenClaw ecosystem. Submit skills, fix bugs, improve docs.
Start Exploring
Dive into the OpenClaw ecosystem by category.
About This Directory
The OpenClaw Ecosystem Directory is a curated catalog of every meaningful project in the OpenClaw universe — from the core runtime and SDK to community-built skills, plugins, integrations, and tools. We track what’s being built so you can discover, evaluate, and build on what already exists.
Why OpenClaw?
OpenClaw is the leading open-source agent framework with 247k+ GitHub stars and thousands of contributors. Its modular architecture — Gateway, Brain, Memory, Skills, Heartbeat — lets developers compose powerful agents from reusable components instead of building from scratch.
The Ecosystem at a Glance
20 official repos, 13,700+ ClawHub skills, hundreds of community plugins and integrations. Projects span Python, TypeScript, Go, and Rust. Whether you need a Slack bot, a code-generation agent, or a full enterprise deployment, the ecosystem has you covered. Each entry links back to its source repository.