Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Macos Local Voice
This skill enables local speech-to-text and text-to-speech functionality on macOS using built-in Apple features.
Saa Agent
This skill allows AI agents to generate images using a specific backend application called the Character Select Stand Alone App (SAA).
Shopify Bulk Upload
This skill helps you upload products to your Shopify store in bulk.
Apple Contacts
This skill helps you find and view contact information stored in your macOS Contacts application.
Mlx Stt
This skill performs speech-to-text conversion using local machine learning models.
Pattern Finder
This skill helps you find commonalities between two different sources of information.
Agent Builder
This skill helps you build high-performing agents for the OpenClaw platform.
Clawd Modifier
This skill is designed to help modify the appearance of a digital mascot named Clawd.
Zapier Mcp
This skill allows you to connect over 8,000 applications using the Zapier service.
Argus Edge
This skill provides an edge detection and betting strategy for prediction markets.
Audit Code
This skill analyzes code for security weaknesses like hardcoded secrets and dangerous function calls.
Cabin Sol
This skill acts as a tutor and builder for Solana development.
Context Sentinel
This tool helps manage different AI model settings based on your current activity.
Contextkeeper
This skill helps AI agents safely track their project state.
Country Info
This skill retrieves information about countries, such as population, languages, currencies, and flags, using an online API.
Dependency Audit
This skill performs a health check on your project's dependencies, identifying outdated packages, unused libraries, and suggesting an update plan.
Lofy Home
This skill helps control smart home devices and manage scene modes like study, chill, sleep, morning, and grind for the Lofy AI assistant.
Meme Signal
This skill provides signals for meme coin trading.
Norman Tax Deduction Finder
This skill helps you find potential tax deductions by analyzing your financial transactions and suggesting how to categorize them.
Session State Tracker
This skill helps manage application data so it persists even after the application is closed and reopened.
Task Sync
This skill helps you keep your tasks synchronized between TickTick and Google Tasks.
Text Detection
This skill helps analyze and detect text that has been generated by artificial intelligence.
Us Value Investing Framework
This skill helps users value US stocks using financial report data, supporting both English and Chinese.
Wangwu Agent Chat
This skill provides a command-line interface for messaging using the Nostr protocol, acting as a decentralized alternative to platforms like WeChat.
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.