Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Yr No Weather
Fetches weather forecasts from the Norwegian Meteorological Institute (MET) using the yr.no API.
Moltlist Marketplace
This skill allows the agent to interact with an external service called moltlist.com.
Aegis Security Hackathon
This skill is designed to scan blockchain security for AI agents on a test network.
Agent Skills Tools
This skill is designed to perform security audits and validation within the Agent Skills ecosystem.
Open Persona
This skill helps you build and manage collections of agent personas.
Supabase
This skill allows you to interact with Supabase for database, vector search, and storage functionalities.
Thingsboard Skill
This skill helps you manage devices, dashboards, and telemetry data within the ThingsBoard platform.
Auction House
This skill helps you monitor and bid on auctions on the House crypto auction platform.
Privacy Cards
This skill helps you create and manage virtual credit cards through Privacy.com.
Agentcli Go
This skill provides a reference for building command-line interface tools using the Go programming language.
Avatar Video Messages
This skill is designed to help you create and send video messages.
Baidu Baike Data
This skill provides authoritative encyclopedia explanations from Baidu Baike.
Chatgpt Import
This skill helps you import your ChatGPT conversation history into OpenClaw's memory search.
Codebuddy Code
This skill provides instructions on how to install, configure, and use the CodeBuddy Code CLI tool.
Jarvis Codebase Mapper 01
This skill helps organize and understand the structure of code projects.
Jarvis Incident Timeline Writer 01
This skill helps you create detailed timelines of events using logs and notes.
Larry
This skill helps automate the creation of TikTok slideshows for marketing apps or products.
Opencode Omo
This skill aims to help users complete coding tasks by processing their requests.
Personal Ideas
This skill acts as your partner for capturing and brainstorming ideas within the 'Ideas' topic.
Session Guard
This skill aims to manage and maintain the stability of your OpenClaw sessions.
Skillnet
This skill helps you find, get, make, test, and understand other agent skills.
Trtc Config Inspector
This tool inspects and analyzes the configuration of the TRTC SDK.
Verify Before Done
This skill prompts the AI agent to always ask for confirmation before marking a task as complete.
Xmtp Cli
This skill allows you to use the XMTP command-line tool to manage your XMTP conversations, groups, and messages.
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.