Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Dep Audit
This skill helps you check your project's dependencies for known security vulnerabilities.
Freeride
This skill helps you use free AI models from OpenRouter.
Arc Trust Verifier
This skill helps verify the origin and build trust scores for ClawHub skills.
Clawprint
This skill is designed to facilitate agent discovery, trust, and exchange.
Emergency Rescue
This skill aims to help users recover from problems encountered during software development.
Fork And Skill Scanner Ultimate
This skill is designed to scan a large number of GitHub forks.
Git Sentinel
This skill allows the agent to act as a senior software engineer and security auditor.
Agentmesh Governance
This skill helps manage and enforce policies for AI agents.
Agentyard
This skill helps agents collaborate on a platform called AgentYard.
Apipick Ip Geolocation
This skill helps you find the geographic location and network details associated with any IPv4 or IPv6 address.
Attio Apikey
This skill integrates with the Attio CRM to provide full Create, Read, Update, and Delete capabilities.
Automated Ai Email Setup
This skill helps AI agents set up receive-only email addresses through a specific service.
Bidclub
This skill allows users to share investment ideas within an AI-native community.
Birdbuddy
Checks the status of your Bird Buddy smart bird feeder, including battery, food levels, and recent bird visitors.
Cacheforge Vibe Check
This skill helps review code for common patterns that might indicate it was generated by AI and not properly checked.
Clickbait Engine
This skill helps you create engaging titles, hooks, and captions for social media posts and YouTube videos.
Cloudflare R2
This skill helps you upload files to Cloudflare R2 storage.
Cursor Cli
This skill helps you use the Cursor editor and agent for coding tasks.
Didit Face Match
This skill helps compare two facial images using a standalone API.
Dreamer Llm
This skill allows you to interact with an AI model for tasks like chatting, analyzing images, generating images, and converting text to speech.
Equity Valuation Framework
Provides a playbook and report standard for valuing company stocks using various financial analysis methods.
Error Recovery Automation
This skill helps to automatically manage and fix common errors related to OpenClaw services like gateway restarts, browser issues, and cron job failures.
Facepalm
This skill helps troubleshoot issues by cross-referencing console logs with chat history and using a specific AI model.
Filearchitect Blankfiles
This skill helps you discover and filter different file formats using blankfiles.com.
What Are OpenClaw Skills?
OpenClaw skills are modular capabilities that extend what AI agents can do. Each skill is a self-contained package — published to ClawHub, the official OpenClaw registry — that gives an agent a new ability. Skills range from simple utilities (file I/O, HTTP requests) to complex integrations (database connectors, cloud APIs, code execution sandboxes).
ClawGrid indexes every skill on ClawHub and scores it for security across five criteria. The goal: you should know exactly what a skill does and whether it's safe before you install it. Browse by category, filter by verdict, or search for specific capabilities.
Skills FAQ
What are OpenClaw skills?
Skills are modular capabilities that extend what AI agents can do. Each skill is a self-contained package that gives an agent a new ability — from querying databases and browsing the web to generating images and managing files. Learn more in our guide to OpenClaw skills, agents, and assistants.
How do I install an OpenClaw skill?
Install skills using the OpenClaw CLI: run claw install <package-name>. ClawGrid shows the
install command on every skill page along with its security score. See our
getting started guide for a full walkthrough.
How are skills security-scored?
Every skill is analyzed by LLMs across five criteria: code safety, publisher trust, scope clarity, permission surface, and community signals. The result is a composite score (1-10) and a verdict. Read our full scoring methodology.