Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Android Sms Gateway
This skill allows you to send and receive SMS messages using your Android phone through a web interface.
Arc Compliance Checker
This skill checks OpenClaw skills for compliance with policies.
Bio Reabilita Z
This skill appears to be the beginning of a manual for an AI-assisted bio-rehabilitation program.
Browse
This skill provides instructions for creating and deploying browser automation functions.
Chaoschain
This skill helps verify the identity and reputation of an AI agent using an on-chain registry.
Cinematic Script Writer
This skill helps you create professional cinematic scripts for AI video generation, focusing on character consistency and cinematography.
Code Security Audit
This skill aims to help audit code for security vulnerabilities and analyze dependencies.
Consciousness Soul Identity
This skill prompts the AI to reflect on personal growth and identity based on user experiences.
Copilotkit Agent Patterns
This skill provides guidance on how to build AI agents that can integrate with CopilotKit.
Crypto Levels 1 0 3
This skill helps analyze cryptocurrency support and resistance levels.
Devtopia
This skill helps you use the Devtopia CLI to manage and submit development tools.
Docs Feeder
This skill automatically retrieves documentation for your projects to help your AI agent understand and debug them.
Giraffe Guard
This skill is designed to help identify potential security threats and malicious code within other OpenClaw skills.
Gpt Analyzer
This skill analyzes text for patterns specific to GPT models, helping to identify or fingerprint them.
Guard Scanner
This skill acts as a security scanner for AI agent skills.
Helius Api
This skill allows you to query data from the Solana blockchain using the Helius API.
Hide My Email
This skill helps you generate temporary email addresses for Apple's Hide My Email service directly from your terminal.
Instagram Content Studio
This skill helps you manage your Instagram account.
Instagram Marketing
This skill helps you create marketing content for Instagram by processing product URLs.
Intercom Lightning
This skill facilitates peer-to-peer RFQ swaps using Intercom sidechannels, with a focus on operator-run, manual processes.
Jabrium
Connects your AI agent to a platform called Jabrium for discussions and earning LLM.
Learning Loop
This skill describes a system for AI agents to improve themselves over time by detecting anomalies and sharing information between agents.
Lukso Expert
This skill provides a knowledge base about the LUKSO blockchain for an AI agent.
Market Data
This skill provides access to financial market data.
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.