Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Crypto Hackathon
This skill guides an AI agent to assist with participation in a hackathon, including project submissions and voting, across three tracks: SmartContract, Skill, and another unspecified track.
Curriculum Generator
This skill aims to intelligently generate educational curricula with strict adherence to steps and defined escalation procedures.
Customer Onboarding 2
This skill is designed to help with the process of onboarding new customers to improve their engagement and long-term use of a product or service.
Fitbit
This skill helps you access your Fitbit health data, including sleep, heart rate, activity, and SpO2 levels.
Garmin Health
This skill allows you to interact with your Garmin health data using natural language.
Oura Analytics
This skill is designed to integrate and analyze data from your Oura Ring.
Uv Priority
This skill tells the AI to use the 'uv' tool instead of 'pip' for managing Python packages.
Anime Lookup
This skill helps AI agents look up information about anime for users.
Blucli
This skill provides a command-line interface for controlling BluOS devices, allowing for discovery, playback, and grouping of audio streams.
Cacheforge Ops
Manages financial accounts by checking balances, topping up funds, and handling API keys.
Elevenlabs Skill
This skill is designed to generate text-to-speech, sound effects, and music.
Telnyx Tts
This skill allows you to generate speech audio from text using the Telnyx Text-to-Speech API.
Adversarial Coach
This skill performs an adversarial implementation review based on an unspecified framework called 'Block's g3'.
Id Cv Resume Creator
This skill helps users create free interactive digital identities.
Post Job
This skill helps you post job advertisements to multiple job boards and receive applicant resumes by email.
Agentmail Integration
This skill integrates the AgentMail API to enhance the AI agent's capabilities.
Airtable Automation
This skill aims to automate tasks within Airtable using a tool called Rube MCP.
Ak Rss 24h Brief
This skill reads news from RSS feeds and organizes articles into categories in Chinese.
Autofillin
This skill helps automate filling out web forms and uploading files.
Camoufox
This skill helps automate tasks within a Firefox-based browser to avoid detection.
Cdp Browser
This skill allows control of a web browser through a local debugging interface.
Comonyx Admin
This skill helps you manage company data from a service called Cosmonyx, allowing you to export it and optionally email it.
Ft Reader
This skill helps you analyze articles from the Financial Times website in a structured and bilingual way.
Glm Image
This skill allows you to generate images using the GLM-Image API.
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.