Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Stonebornbot
This skill aims to automate the process of minting NFTs on Ethereum and other EVM-compatible blockchains.
Summarize File
This skill reads text files from your computer and creates short summaries of their content.
Telnyx Rag
This skill allows you to search and ask questions about your files using AI and a service called Telnyx Storage.
Tex Render
This skill converts LaTeX math formulas into image files like PNG, JPEG, WebP, or AVIF.
Vincent Brave Search
This skill allows you to search the web and news using Brave Search.
Visual Rpa Skill
This skill is designed to automate tasks on your desktop using visual recognition.
Vn Market News Monitor
This skill monitors financial news and market trends in Vietnam.
Web Bundling
This skill helps you package web applications into a single HTML file for easier sharing.
Web I18n Nextjs
This skill provides guidance on implementing internationalization (i18n) for Next.js and Node.js web applications using the App Router.
Web Navigator
This skill is intended to help you navigate the web, but its functionality is not yet defined.
Web Search With Serpapi
This skill allows you to search the web using various search engines through the SerpAPI service.
Wechat Search Release
This skill helps you search for articles from WeChat Official Accounts using web search and fetching capabilities.
Wrynai Skill
This skill helps OpenClaw perform advanced web crawling and content extraction using the WrynAI SDK.
Alchemyst Mcp
This skill allows the AI to store, retrieve, search, and view persistent context using the Alchemyst AI MCP.
Anterior Cingulate Memory
This skill is intended to help detect conflicts and monitor for errors.
Arc Skill Health Monitor
This skill monitors the performance and error rates of other deployed skills.
Auteng Docs Curl Publish
This skill helps you publish markdown content and get shareable links using the curl command.
Azure Ai Agents Py
This skill helps you build AI agents using the Azure AI Agents Python SDK.
Citrineos Assistant
This skill helps you manage your EV charging station software, CitrineOS, using natural language commands.
Coala
This skill helps you use a command-line tool called coala-client to chat with AI models and other services.
Construction Pm
This skill provides a toolkit for AI agents to manage construction projects.
Depguard
This skill helps audit software dependencies for security vulnerabilities and license compliance.
Elasticsearch Skill
This skill allows you to interact with Elasticsearch and Kibana using the curl command-line tool.
Gmail Tool
This tool allows you to send and receive emails using your Gmail account.
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.