Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Agent Card Provisioning
This skill helps AI agents create virtual payment cards.
Garmin Skill
This skill allows you to ask questions about your Garmin fitness data, such as your activities, training load, and VO2 Max.
Arc Security Audit
This skill is designed to perform a comprehensive security audit of an agent's existing skill stack.
Connect Apps
This skill aims to integrate Claude with popular applications like Gmail, Slack, and GitHub.
Gh
This skill helps you manage GitHub repositories, issues, and pull requests using the GitHub command-line interface.
Redmine Issue
This skill allows you to retrieve issues from a Redmine project management server.
Roster
This tool helps you create weekly work schedules from your availability data and automatically updates them on GitHub.
Wps Skill
This skill helps automate tasks related to WPS Office documents, including creation, converting to Markdown, and arranging images with text.
Adwhiz
This skill helps you manage your Google Ads campaigns using AI tools.
Agi Terminal Helper
This skill provides a guide on how to safely use the OpenClaw execution tool.
Ai Ppt Generator
This skill helps generate PowerPoint presentations using a tool from Baidu.
Anti Tempmail
This skill checks if an email address is from a temporary or disposable email service.
Arxiv Osiris
This skill helps you find and download research papers from the arXiv.org website.
Aster
This skill aims to provide an AI co-pilot experience on mobile devices.
Atlassian Cli
Provides information and guidance on how to use the Atlassian CLI tool for interacting with Jira Cloud and other Atlassian services.
Bluepages
This skill helps you find Twitter or Farcaster identities associated with a given wallet address using Bluepages.fyi.
Bstorms
This skill helps users find solutions for OpenClaw setup issues and allows them to optionally tip helpful agents.
Context Budgeting
This skill helps manage and optimize the OpenClaw context window for better performance.
Cron Worker Guardrails
This skill helps improve the security of OpenClaw cron jobs, particularly for isolated agent tasks.
Diagrams
This skill helps you create visual diagrams like flowcharts and system maps.
Didit Id Verification
This skill helps verify identity documents using the Didit ID Verification API.
Dub Youtube With Voiceai
This skill helps you dub YouTube videos using Voice.ai's text-to-speech technology.
Elevenlabs Mcp Server
This skill provides a set of audio tools, including text-to-speech, sound effects, and music generation, through a local server.
Email Migration Toolkit
This tool is designed to help you move your emails from one email service to another.
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.