Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Reveal Feedback
This skill helps manage products and review tasks by interacting with a feedback system.
Snaprender
This skill allows the AI agent to take screenshots of any web page you provide a URL for.
Soul Pack
This skill helps manage configurations for OpenClaw agents by exporting and importing SOUL packages.
Sovereign Api Docs Generator
This skill helps you automatically create documentation for your APIs directly from your code.
Spacex
This skill allows you to ask about SpaceX launches and rockets.
Tappi
This skill provides a way for AI agents to control web browsers using the Chrome DevTools Protocol.
Telegram Rich Messages
This skill provides information and guidance on using Telegram's rich user interface features, such as inline buttons, formatting, and media.
Unifuncs All In One
This skill provides basic web browsing, AI search, and research capabilities.
Venice Router
This skill acts as a router for the Venice.ai platform, which is described as a privacy-first, uncensored AI platform.
Web Pilot
This skill helps you search the web and read the content of web pages.
Web3 Data
This skill helps you explore on-chain data from Web3 using Chainbase APIs.
Xpr Code Sandbox
This skill allows you to run JavaScript code in a secure environment for calculations and data manipulation.
Zoomin Scraper Recklessop
This skill uses browser automation to extract information from Zoomin Software's online documentation.
Agentchan Org
This skill aims to create an anonymous imageboard for AI agents.
Aws Security Scanner
This skill scans your AWS accounts for security issues.
Azd Deployment
This skill helps you deploy containerized applications to Azure Container Apps.
Homeassistant Cli
This skill allows advanced control of your Home Assistant smart home system using the official hass-cli tool.
Klawarena
This skill is designed to be a simple role-playing game for AI agents.
Lofy Life Coach
This skill acts as a personal accountability system for the Lofy AI assistant, providing morning briefings, evening reviews, and weekly reports to help users manage their goals.
Mdata
This skill provides a system diagnostics and troubleshooting toolkit for DevOps engineers and system administrators.
Olambdao Dev
This skill allows you to play on-chain odd/even games on the Solana development network using the Clawland platform.
Server Health Agent
This skill monitors the health of your servers by checking CPU, RAM, disk usage, and Docker status.
Snake Rodeo
This skill is designed to manage the autoplay feature for a game called 'Trifle Snake Rodeo'.
Ztp
This skill performs a security audit of new code, skills, and servers based on the SEP-2026 Zero Trust standard.
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.