Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Opendart Disclosure
This skill retrieves financial disclosure information from Korea's OpenDART system.
Overlap Check
This skill helps you check for existing issues and pull requests before creating new ones.
Qwen3 Tts Voicedesign
This skill provides text-to-speech functionality using the Qwen3-TTS VoiceDesign model.
Requesting Code Review
This skill guides the AI agent to review code, implement features, and verify work before merging.
Roundtable Adaptive
This skill facilitates a multi-model AI discussion.
Sealegs Marine Forecast
Provides AI-powered marine weather forecasts for any location worldwide.
Seedance Guide
This skill acts as a director for a tool called Seedance 2.0, likely to help with creating storyboards.
Seedance2 Skill
This skill is a placeholder for a video creative studio, offering no specific functionality at this time.
Simple Redux
This skill helps you format text according to specific style guidelines.
Skillguard Scanner
This skill is designed to scan other skills within the OpenClaw/ClawHub ecosystem for security vulnerabilities.
Smart Models
This skill helps select the best AI model for different tasks, such as image processing.
Supernal Interface
This skill provides a framework for making applications controllable by AI.
Swift Patterns
This skill helps you write, refactor, and improve SwiftUI code for iOS and macOS applications.
Teamo Strategy
This skill acts as a cognitive task decomposer and strategic commander for an AI agent.
Terrain Route Video
This skill helps you create a simple animated driving route video from a list of cities or points of interest.
Tidbyt Status
This skill creates a local web server to show the status of the OpenClaw agent on your Tidbyt LED display.
Travel Destination Brochure
This skill helps you create travel brochures and scenarios based on a city name.
Venice Models
This skill helps you discover and learn about various AI models offered by Venice AI, including text, image, video, and audio generation.
Xerolite
This skill aims to integrate two tools, OpenClaw and Xerolite, specifically for use with Interactive Brokers.
Computational Humor
This skill provides AI agents with information on humor patterns based on embedding space bisociation theory.
Markitdown Skill
This skill helps convert documents into Markdown format.
Copilotkit React
This skill provides guidance on best practices for using CopilotKit React in agentic applications.
Create Hat Collection
This skill helps you create new preset collections for Ralph hats.
Dgr
This skill helps generate decision artifacts for LLM outputs, including assumptions and risks.
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.