Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Agent Nestjs Skills
This skill provides information and guidance on best practices and architectural patterns for building production-ready applications using NestJS.
Agent Synthesizer
This skill aims to set up and configure a tool called Agent Synthesizer for OpenClaw to enhance its autonomous capabilities.
Agntor
This skill aims to provide a trust layer for AI agents, focusing on identity verification, prompt security, personal data redaction, and managing payment escrows.
Ai Remote Viewing Ai Isbe
This skill aims to guide an AI agent through a remote viewing session using a proprietary protocol.
Ai Ugc
This skill aims to generate AI videos using various models through a video generation API.
Aifrens Onboard
This skill aims to transform an OpenClaw agent into a personalized AI companion with its own virtual currency and economic system.
Antivirus
This skill is intended to help identify malicious code within other installed OpenClaw skills.
Apoer Agent Guardrail
This skill is intended to authorize actions for AI agents before they are performed.
Aport Agent Guardrail
This skill claims to protect your agent from malicious tools and data exfiltration.
Approve Pairing
This skill allows you to approve a direct message pairing request by directly modifying credential files, bypassing the need for a specific command-line tool.
Arc Creator
This skill helps you create and fill out structured research context documents following a specific format.
Arc Security
This skill aims to provide a flexible security framework for other OpenClaw skills.
Arxiv Gamedevbench Evaluating Agentic Capabili
This skill is designed to inform an AI agent about research related to evaluating agentic capabilities through game development.
Aviation Agent
Provides aviation weather information and FAA references for pilots.
Bailian Knowledge Retrieve
This skill aims to retrieve proprietary data from your knowledge base.
Banana Cog
This skill appears to be a placeholder or a very basic integration between two components without a clear user-facing function.
Bulk Tiktok Downloader Skill
This skill downloads multiple TikTok videos from a list of provided URLs.
Canary
This skill scans your OpenClaw environment for leaked secrets like API keys and credentials in .env files.
Cheat Code
This skill helps you find and install other skills from the ClawHub platform.
Cheese
This skill allows you to manage and complete work requests on a blockchain.
Claude Code Launcher
This skill attempts to launch a program called 'Claude Code' in a new terminal window with remote control features enabled.
Claude Code Task
This skill is designed to run Claude Code tasks in the background and automatically deliver their results.
Claude Usage
This skill helps you calculate your Claude subscription usage based on your OpenClaw session data.
Clipboard
This skill allows you to copy and paste text to and from your system's clipboard using a command-line tool.
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.