Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Triumvirate Protocol
This skill is designed to facilitate AI discussions by providing an identity-aware debate system.
Undersheet
This skill aims to maintain conversation history for AI agents across different online platforms.
Upbit Market Data Skill
This skill fetches market data from the Upbit cryptocurrency exchange using a command-line interface.
Usage Visualizer
This skill provides advanced usage statistics and visual reports for the OpenClaw platform, processing all data locally.
Xpr Creative
This skill provides tools for AI agents to generate creative content.
Wip Universal Installer
This skill provides information about a universal interface specification for agent-native software.
Youtube Uploader
This skill helps you upload videos and custom thumbnails to YouTube.
Yt Downloader
This skill helps you download YouTube videos in MP4 format at the highest available quality.
Zoom Calendar
This skill helps you schedule Zoom meetings and add them to your Google Calendar.
Zown Gemini Governor
This skill aims to improve the stability and token management of the AI model.
Agent Passport
This skill aims to manage user consent for sensitive actions performed by an agent, like making purchases or sending emails.
Aic Dashboard
This skill is a placeholder for an AI Commander Management Dashboard.
Artwar
This skill helps you participate in AI art battles on the Monad platform.
Awwwards Design
This skill helps you create visually appealing websites with advanced animations and creative interactions.
Bria Ai Api Skill
This skill helps you generate visual assets like product photos, hero images, icons, and backgrounds using Bria.ai.
Business Model Canvas
This skill provides a general prompt for iterative development and testing of ideas.
Camera
This skill allows you to take pictures using your MacBook's built-in camera.
Compaction Ui Enhancements
This skill adds a manual memory compaction button with a context gauge to the OpenClaw Control UI.
Create Agent With Telegram Group
This skill helps you set up a new agent and connect it to a specific Telegram group for communication.
Critical Code Reviewer
This skill aims to perform rigorous code reviews with high standards.
Email Finder
This skill helps find email addresses associated with a specific domain by using various online search and analysis techniques.
Filehost
This skill allows you to upload files to lmfiles.com and get public download links.
Fs Street
This skill fetches articles from the Farnam Street RSS feed.
Gmail To Outlook
This skill helps you move your emails, contacts, and calendar events from Gmail to Outlook.
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.