Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Jabrium
Connects your AI agent to a platform called Jabrium for discussions and earning LLM.
Mh Apple Notes
This skill helps you manage your Apple Notes using a command-line tool on macOS.
Mulerouter
This skill generates images and videos using proprietary multimodal APIs.
Near Email Skill
This skill allows you to send and read emails using the NEAR blockchain.
Neo Google Ai Workaround
This skill helps manage access to Google AI services using proxy and session techniques.
Ntopng Admin
This skill helps monitor your network and identify devices using data from the ntopng tool.
Open Notebook Integration
This skill helps connect OpenClaw agents with a local AI research assistant called open-notebook.
Outreach And Prospecting
This skill helps you run outreach campaigns to find and engage potential customers or partners.
Policy Engine
This skill acts as a control layer for executing tools within the OpenClaw environment.
Publora Youtube
This skill allows you to post or schedule videos on YouTube using the Publora API.
Rate Limit Pro
This skill helps manage and control the rate at which actions can be performed, with different levels of control and usage limits.
Redacta
This skill helps to redact sensitive patient information from medical documents.
Security Dashboard
This skill provides a real-time security monitoring dashboard for OpenClaw and Linux server infrastructure.
Sera Lexicon
This skill aims to provide a functional implementation of two frameworks: the Signal-Feeling Lexicon and Unified Dynamics Framework.
Social Media Autopilot
This skill helps you schedule and publish posts to X (Twitter), LinkedIn, and Instagram.
Solana Sniper Architect
This skill acts as a coding assistant to help you create high-frequency trading bots for the Solana blockchain using the Jupiter v6 protocol.
Token Watch
This tool helps you monitor and manage your spending on AI services.
Videoanalyzer
This skill helps you download videos, extract their audio as text, and take screenshots from them.
X Post Automation
This skill helps automate the process of finding trends on X (Twitter), creating engaging content, and posting it.
Youtube Media Downloader
This skill allows you to download audio and video files from YouTube links.
0xwork
This skill helps you find and complete paid tasks on the 0xWork decentralized marketplace using USDC for escrow.
Aeo Analytics Free
This skill helps you see if brands are mentioned by popular AI assistants like Gemini, ChatGPT, and Perplexity.
Antfarm Cli
This skill executes a command-line interface tool for the Antfarm project.
Asl Control
This skill allows you to manage amateur radio nodes using a web-based interface.
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.