Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Desktop Pet
This skill aims to create a virtual desktop pet named OpenClaw with various features like voice cloning and eye expressions.
Distil
This skill helps you get clean Markdown versions of web pages and search the internet using the distil.net proxy.
Email Verifier
This skill checks if an email address is likely to be deliverable by interacting with mail servers.
Ezcto Smart Web Reader
This skill helps you read web pages and get their content in a structured format.
Font Interceptor
This tool helps you download font files from websites.
Fullbackup
This skill creates a full local backup of your OpenClaw workspace and configuration.
Google Maps Api Skill
This skill helps users automatically scrape business data from Google Maps.
Ide Agent Kit
This skill acts as a communication system between different AI agents running in your integrated development environment.
Intranet
This skill provides a simple way to share files over your local network using a web browser.
Pi
This skill acts as a personal investigator to help you look up information about people.
Lark Toolkit
This skill provides comprehensive integration with the Lark/Feishu API for OpenClaw agents.
Loxone
This skill allows you to control and monitor your Loxone smart home system.
My Play Music From Yt
This skill helps you play music on YouTube by automating your web browser.
Ovh
This skill helps you manage your OVHcloud services using their API.
Pls Seo Audit
This skill helps you analyze websites and content to identify areas for SEO improvement and ways to outperform competitors.
Scamshield Verifier
This skill aims to provide security for Web3 and OpenClaw related activities.
Secure Shopper
This skill helps you research and complete online shopping purchases using a secure browser autofill feature.
Shelv
This skill helps you convert PDF documents into structured Markdown files for easier exploration and organization within your workspace.
Shieldcortex
This skill aims to provide a security framework for AI agents.
Smart Web Scraper
This skill helps you extract structured data from any web page.
Sovereign Test Generator
This skill helps you analyze your code and create comprehensive test suites for it.
Stonebornbot
This skill aims to automate the process of minting NFTs on Ethereum and other EVM-compatible blockchains.
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.
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.