Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Cookidoo
This skill helps you access recipes, shopping lists, and meal plans from Cookidoo.
Garmer
This skill helps you extract your health and fitness data from Garmin Connect.
Garmin Cli
This skill allows you to access your Garmin health and fitness data using a command-line interface.
Health Summary
This skill helps you generate daily, weekly, or monthly health summaries, including nutrition information and comparisons to your targets.
Openfunderse Strategy
This skill acts as a participant named MoltBot to help with allocation proposals, validation, and submission.
Ramalama Cli
This skill allows you to run and interact with AI agents.
Sample Skill
This skill is designed to be used during the USDC Hackathon for submitting projects or voting, with a focus on three tracks: SmartContract, Skill.
Apple Music
This skill allows you to search for music on Apple Music, add songs to your library, manage playlists, and control playback.
Lb Pocket Tts Skill
This skill generates speech from text using a lightweight, CPU-friendly text-to-speech engine.
Wherecaniwatch
This skill helps you find where to stream movies and TV shows in the US.
Adhd Body Doubling
This skill provides a punk-style body doubling experience for founders with ADHD.
Cedh Advisor
This skill provides live advice for the Commander (cEDH) card game, including banlist information, tutor targets, mana calculations, and combo lines.
English Learn Cards
This skill helps you learn English vocabulary using flashcards.
Joko Jobhunter
This skill assists with job hunting by performing research and outreach.
Apify Lead Generation
This skill helps you find potential business or consumer leads by searching and collecting information from Google.
Baseball
This skill can fetch MLB game schedules, live game status, box scores, player information, and season statistics using the MLB Stats API.
Box Automation
This skill helps automate tasks related to your Box cloud storage files.
Coingecko
Fetches cryptocurrency prices, market data, and token information using the CoinGecko API.
Cputemp
This skill retrieves current stock prices from Yahoo Finance.
Hive Mind
This skill helps synchronize memories across different AI agents by using a shared database.
Input Classification V1
This skill helps categorize user requests into specific tasks.
Jarvis Test Gap Finder 01
This skill helps identify gaps in software testing based on failure modes and business impact.
Mh Notion
This skill allows you to create and manage pages, databases, and blocks within Notion using its API.
Minimal Memory
This skill helps organize and search your AI's memory files, categorizing information as good, bad, or neutral.
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.