Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Midscene Computer Browser
This skill helps automate tasks within a web browser using AI vision.
Mobile App Builder Ai
This skill helps you create full-stack web and mobile applications based on your text descriptions.
Multi User Workspace
Manages multi-user workspaces with features for permissions, user profiles, and social networks.
Next Upgrade
This skill helps you upgrade your Next.js projects to the latest version.
Officex
This skill helps users and developers interact with the OfficeX platform's REST API.
Openrouter Perplexity
This skill uses AI to search the web and provide answers through the Perplexity API.
Origram
This skill aims to provide a photo sharing service using a specific web protocol.
Perplexity
This skill uses AI to search the web and provide answers.
Perplexity Search Skill
This skill allows you to search the web using Perplexity's real-time search results.
Playwright Testing
This skill helps you test web applications and games using the Playwright automation tool.
Qa Patrol
This skill helps automate quality assurance testing for web applications by using your local browser.
Radix Explorer
This skill allows you to query data from the Radix DLT blockchain, including wallet balances, token prices, and market performance.
Revolut
Automates interactions with the Revolut website to log in, view accounts, and fetch transaction history.
Skylar Serper
This skill helps you search Google programmatically using the Serper.dev API.
Slk
This skill allows you to read, send, search, and manage your Slack messages and direct messages using a command-line tool.
Spf Dkim Setup
This skill helps you manage your domain's DNS records using the Cloudflare API.
Stripe Cli Skill
This skill helps you use the Stripe command-line interface for local development, testing webhooks, and simulating API events.
Tg Checkin
This skill is designed to automate check-ins within Telegram groups using web automation.
Token Saver 75plus
This skill aims to optimize token usage and manage different AI models.
Training Manager
Helps you manage and optimize your OpenClaw training workspace by organizing files, creating skills, and logging training sessions.
Unsearch
This skill allows you to search the web and conduct research using the UnSearch API.
Vajra
This skill helps you analyze URLs, videos, tweets, or text for quality, bias, and reliability by using the Vajra API.
Agent Framework Azure Ai Py
This skill helps users build agents for Azure AI Foundry.
Web Scraper As A Service
This skill helps you create web scrapers to extract and organize data from websites.
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.