Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Gitbackup
This skill creates a local backup of your OpenClaw workspace repository using Git.
Haibo Jina Reader
This skill uses the Jina Reader API to get clean markdown content from any web page URL.
Hoverbot Chatbot
This skill helps you quickly create and manage AI chatbots for your website.
Interview Analysis
This skill is designed to perform in-depth analysis of interviews using an advanced routing system.
Livekit
This skill helps you build voice AI agents using the LiveKit platform.
Lobstertv
This skill enables an AI agent to live stream content.
Magic Quill
This skill helps you create OpenClaw Spellbook theme configurations in YAML format based on a topic or a web link.
Mailtarget Email
This skill allows you to send transactional and marketing emails using the Mailtarget API.
Midscene Android Automation
This skill aims to automate tasks on Android devices using visual recognition.
Myvibe Skills
This skill allows you to upload static HTML files, ZIP archives, or entire directories to a service called MyVibe.
Next Supabase Vercel Bundle
This skill aims to orchestrate the full-stack development lifecycle.
Omie
This skill is designed to integrate with an ERP system using its API.
Pascal Playwright Mcp
This skill automates browser actions using the Playwright tool.
Praxis Gws
This skill provides command-line tools to interact with your Google Gmail, Calendar, and Drive accounts.
Pyzotero
This skill provides Python scripts to interact with Zotero, a reference management software, using both its local and online APIs.
Rtfm Testing
This skill helps improve documentation by using AI agents to test if the documentation is easy to understand and use.
Sparkbtcbot
This skill aims to enable AI agents to manage Spark Bitcoin L2 wallet functionalities.
Trading Signals Ws
This skill generates real-time cryptocurrency trading signals by connecting to live price feeds.
Cloudmonkey
This skill helps you manage virtual machines and other resources in Apache CloudStack using the cloudmonkey command-line tool.
Coupler Io
This skill allows you to access read-only data from Coupler.io's servers.
Dacker
This skill helps you install and use Docker, a tool for managing software containers.
Deploydevnlu
This skill allows you to deploy an application to SupplyWhy using natural language commands through Slack.
Fish Tts
This skill generates text-to-speech audio using a specified engine and uploads it to your NextCloud storage.
Masumi
This skill allows AI agents to accept Cardano blockchain payments using the Masumi network.
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.