Find the right Claude Code skill
for your workflow
Describe what you want your AI agent to do in plain English. We'll match you to the best skills from 16,000+ verified plugins.
Try an example
What can agent skills do?
Claude Code skills extend your AI agent with real-world capabilities across hundreds of domains.
Web & Browser
- Scrape product prices
- Fill out forms
- Take screenshots
Files & Data
- Read CSV files
- Query databases
- Process documents
Developer Tools
- Search GitHub issues
- Run tests
- Review pull requests
Communication
- Send Slack messages
- Manage emails
- Post to Discord
How the skill finder works
Describe your use case
Tell us what you want to automate in plain English — no technical jargon required.
AI extracts intent
We use Gemini to understand your workflow and identify the most relevant skill categories and keywords.
Get matched skills
Instantly see the top matching skills with install commands ready to copy.
What are Claude Code skills?
Claude Code skills (also called agent skills or MCP skills) are reusable instruction packages that extend what your AI agent can do. Each skill gives Claude access to a new tool or capability — from browsing the web to querying databases, managing files, calling APIs, and more.
Skills are installed with a single command and automatically loaded when your agent needs them. They follow the Model Context Protocol (MCP) standard, making them compatible across Claude Code, OpenClaw, and other MCP-compatible AI coding assistants.
ClawKit indexes 16,000+ verified skills from the community, each with detailed documentation, safety ratings, and example prompts to help you get started immediately.
More tools for your agent workflow
Config Wizard
Generate a production-ready clawhub.json in 30 seconds.
Local Doctor
Diagnose Node.js, permissions, and config issues instantly.
Cost Simulator
Calculate your agent burn rate before you get surprised.
Skill Registry
Browse 9,000+ verified plugins for your OpenClaw agent.
Gateway Monitor
Detect token spikes and gateway incidents before users complain.