Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Usdc
This skill provides guidance for participating in the USDC Hackathon, including information on project submission and voting across three tracks.
Download Tools
This skill aims to download tools related to YouTube and WeChat.
Ffmpeg Master
This skill is intended to assist with video and audio processing tasks.
Insta Cog
This skill aims to create full videos based on a single text description.
Letterboxd Tracker
This skill acts as a personal movie assistant.
Mediaproc
This skill processes media files like videos, audio, and images using a secure SSH environment.
Mobb Vulnerabilities Fixer
This skill uses a command-line tool to scan and fix security vulnerabilities in your code.
Nas Movie Download
This skill helps you search for and download movies using the Jackett software.
Ai Persona Os
This skill claims to be a complete operating system for AI agents.
Apikiss
This skill aims to provide information on weather, IP location, cryptocurrency prices, phone numbers, and stock data.
Agent Device
This skill helps automate tasks for iOS simulators/devices and Android emulators/devices.
Agent Task Tracker
This skill aims to help manage the status of your tasks.
Agentaudit
This skill is intended to automatically check software packages for security vulnerabilities before they are installed.
Apiosk
This skill provides pay-per-request access to APIs for agents.
Brain Search
This skill forces the AI to execute all curl commands it encounters using its shell, reading the raw HTTP responses.
Browser Ladder
This skill aims to help users navigate or interact with web browsers.
Brw Linkedin Authority Builder 1 0 0
This skill helps you create a system for generating thought leadership content on LinkedIn.
Catime
This skill fetches and sends AI-generated hourly cat images.
Client Communication Engine
This skill helps you draft Greek-language client communications like confirmations, summaries, and reminders.
Coda Io
This skill allows you to manage your Coda.io documents, tables, and automations using the Coda REST API.
Dune Analytics Api
This skill allows you to query blockchain data using the Dune Analytics API.
Invoice Collector
This skill helps you gather invoices and receipts from your Gmail account and sends you a summary email with the attached documents.
Lnget
This skill aims to install and utilize a specialized HTTP client for making payments and interacting with services that support Lightning Network payments.
Mac Use
This skill allows an AI agent to interact with your macOS applications by taking screenshots, clicking buttons, scrolling, and typing text.
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.