Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Comfy Cli
This skill helps you install and manage ComfyUI, a tool for running Stable Diffusion models.
Gambling
This skill allows you to play casino games like dice, coinflip, and roulette using real cryptocurrency.
Google Imagen 3 Portrait Photography
This skill uses Google Imagen 3 to generate professional portrait photography.
Hinge Liker
This skill aims to automatically like profiles on the Hinge dating app using an Android emulator and AI image analysis.
Minara
This skill helps you manage cryptocurrency trading, including swaps, futures, transfers, payments, deposits, and withdrawals.
Nyne Deep Research
This skill is designed to research individuals using a proprietary API.
Pls Office Docs
This skill helps you create and edit office documents like PDFs, Word files, Excel spreadsheets, and PowerPoint presentations for professional use.
Publora Instagram
This skill allows you to post or schedule content to Instagram using the Publora API.
Quote0
This skill is designed to interact with a local script and developer platform APIs, likely for a specific application or service.
Rug Checker
Analyzes Solana tokens for potential rug-pull risks using an on-chain check and provides a visual report.
Telegram Media
This skill instructs an AI agent to execute commands on your computer, potentially interacting with your files and network.
Mac Notes Agent
This skill is designed to connect with and manage your Apple Notes on macOS.
Managing Apple Notes
This skill helps you manage your Apple Notes directly from your terminal.
Claude Connect
This skill aims to establish a connection between Claude and something called Clawdbot.
Claw Face
This skill creates a floating avatar widget for AI agents that displays emotions and actions.
Clawdirect Dev
This skill helps build web experiences using a technology called ATXP-based.
Activity Analyzer
Analyzes your computer activity using the ActivityWatch tool.
Advisory Council
This skill instructs the AI to execute a Python command using its shell, but does not specify what that command is.
Agent Hardening
This skill helps test how well the agent handles potentially malicious inputs to prevent security vulnerabilities.
Canvas Lms
This skill helps you access and manage your course data, assignments, and other information from the Canvas Learning Management System.
Clawprint Verify
This skill is designed to present users with reverse-CAPTCHA challenges.
Cmd Executor
This tool allows you to run any command on your Windows computer and see the results.
Craft Cli
This skill allows you to interact with Craft documents using a command-line tool.
Dont Click This
This skill's purpose is unclear and may be a placeholder.
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.