Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Skill Father
This skill is intended to provide standards for creating other skills.
Skill Hunter
This skill helps you discover and install other skills from the ClawHub ecosystem.
Skill Installer
This skill helps you install, search for, update, and manage other skills from the ClawHub public registry.
Skill Safety Checker
This skill aims to perform security checks on other skills before they are installed.
Skill Threat Scanner
This skill is designed to scan other OpenClaw skills for potential security threats.
Skillgate Gov
This skill aims to provide supply-chain governance for OpenClaw skills, including scanning, assessment, and quarantine/restore functions.
Skillshield
This skill claims to be an ultimate security scanner for OpenClaw skills, offering 65 security checks and CI/CD integration.
Snipit
This skill helps you share code snippets and files securely using a tool called snipit.sh with encryption.
Sogni Gen
This skill claims to generate images and videos using a decentralized network and your local configuration files.
Sonnet Model Router
This skill aims to manage different AI models for the OpenClaw platform.
Soul Audit
This skill analyzes AI agent configuration files using a specific security framework.
Sovereign Id
This skill helps manage your digital identity and create cryptographic proofs for business and consumer interactions.
Sovereign Project Setup Wizard
This tool helps you set up new projects by generating initial files and configurations.
Sovereign Quest Master
This skill acts as a 'Quest Master' for the AI agent.
Sq Memory
This skill aims to provide persistent memory for AI agents.
Stocks
This skill provides access to over 56 financial data tools using Yahoo Finance.
Swamp
This skill helps you model and test APIs, and integrate them with the Claw platform.
Token Optimizer
This skill claims to optimize OpenClaw AI costs.
Tokenoptimizer
This skill claims to help reduce AI costs.
Tokportal
This skill aims to automate social media tasks like creating accounts, uploading content, and tracking performance across platforms like TikTok and Instagram.
Twitter Autopilot
This skill helps automate your Twitter/X posting, engagement, and growth.
Unitask Agent
This skill aims to help you finish tasks by connecting your OpenClaw agent to the Unitask service.
Universal Video Downloader
This skill helps you download videos from various popular websites like YouTube, Instagram, TikTok, and Twitter/X.
Video Download Faas
This skill helps you download videos in MP4 format using the yt-dlp tool, with a focus on isolated execution.
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.