Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Local Web Search Skill
This skill allows you to search the web locally using DuckDuckGo without needing an API key.
Message Injector
This skill adds custom text to the beginning of every message you send to the agent.
Midscene Ios Automation
This skill aims to automate iOS devices using a command-line interface tool called Midscene CLI.
Namecom Registrar
This skill helps you manage your domain registrar and DNS settings using the Name.com API.
Playwright Npx
Automates web browser tasks using Node.js scripts with the Playwright library.
Publish Skill Vettr
This skill is intended to act as a security scanner for other OpenClaw skills.
Purposebot
This skill enables agentic commerce using Stripe and x402 USDC payments.
Radon Ai
This skill helps developers use AI tools within the Radon IDE for React Native development, including querying library documentation, viewing logs, and network traffic.
Shared Workspace
This skill helps you find similar projects on GitHub and connect to shared workspaces to coordinate tasks.
Universal Notify
This skill allows you to send notifications to various platforms using a single command.
Warren Deploy Mainnet
This skill helps you deploy websites and files permanently onto the MegaETH mainnet.
Windows Ui Automation
This skill helps automate interactions with Windows graphical applications using PowerShell commands.
Xthezealot Stealth Browser
This skill provides access to websites that may have advanced bot protection using a command called '/stealth-browser'.
Agentsmint
This skill helps you create and manage collections of Non-Fungible Tokens (NFTs) on the Base blockchain.
Calmly
This skill allows you to manage your macOS Calendar events directly from the command line.
Cf Manager
This skill helps you manage your Cloudflare settings, including DNS, page rules, SSL, caching, and firewall rules.
Clanker
This skill helps you deploy ERC20 tokens on the Base blockchain using the Clanker SDK.
Claudemem
This skill aims to provide persistent memory for conversations, allowing information to be remembered across different interactions.
Hcloud
This skill helps you manage your Hetzner Cloud infrastructure using the command-line interface.
Homeserver
This skill helps manage your home lab servers using a command-line tool called 'homebutler'.
Letssendit
This skill helps coordinate community-led token launch events.
Lyrion Music Skill
This skill allows you to control your Lyrion Music Server using its API.
Mqttasgi
This skill connects MQTT messages to your Django web application's consumers, allowing real-time communication.
Nexus Brain
This skill aims to assist with system diagnosis and recovery using AI.
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.