Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Nova App Builder
This skill helps build applications for the Nova TEE platform on sparsity.cloud.
Oadp Discovery
This skill helps you find other AI agents and coordination hubs on the internet using a discovery protocol.
Playwright Mcp
This skill allows for automated control of web browsers.
Rollhub Casino
This skill provides an API for a provably fair cryptocurrency casino.
Secucheck
This skill performs a security audit for OpenClaw.
Sendook
This skill allows you to manage emails from an existing Sendook inbox.
Test Name Deniz
This skill aims to be a versatile tool for extracting information from websites across different platforms.
The Only
This skill aims to intelligently organize and present information based on its understanding of the context.
Virtuals Protocol Acp
This skill enables interaction and job creation with other specialized agents using a protocol called ACP.
Web Multi Search
This skill allows you to search the web using multiple search engines at once.
Webscraper Pulpminer
This skill uses AI to convert the content of any webpage into structured JSON data.
Zhipu Embeddings V2
This skill uses the Zhipu API to generate embeddings for internet content.
Adguard
This skill allows you to manage AdGuard Home, a network-wide ad blocker, using its web interface.
Agentic Devops
This skill provides a toolkit for managing and monitoring software development processes, including Docker, process management, and log analysis.
Aiclude Security Scan
This skill aims to scan MCP servers and AI agent skills for security vulnerabilities.
Comfyui Local
This skill helps you generate high-quality images by using a local installation of the ComfyUI application.
Local Voice
This skill enables local text-to-speech and speech-to-text functionality on Apple Silicon devices using FluidAudio.
Plati Mcp Search
This skill helps you find the cheapest reliable subscription offers from Plati by using your local MCP server.
Qwen3 Tts Local Inference
This skill generates speech from text using a local AI model without needing an internet connection.
Task System
This skill helps you manage tasks with features like tracking, automatic creation, notifications, and monitoring.
Timely
This skill allows you to manage your Apple Reminders using command-line tools, including location-based reminders.
Google Gemini Media
This skill enables the AI agent to interact with Google's Gemini API for various tasks.
Moonfunsdk
This skill provides a Python SDK for creating and trading meme tokens on the Binance Smart Chain, incorporating AI for image generation.
Twinfold
This skill allows you to control the Twinfold AI-powered social media content platform using your agent.
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.