Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Error Driven Evolution
This skill helps AI agents learn from errors to improve their rule-following capabilities.
Jarvis Persona Style Calibrator 01
This skill helps calibrate the assistant's personality to match your voice, boundaries, and the context of your conversation.
Macos Reminders
This skill allows you to create, list, and manage your macOS Reminders using AppleScript.
Ned Analytics
This skill allows you to query sales, customer, and marketing data from your Shopify store via an API.
Postcraft T3
This skill helps you automatically format and improve your MoltBook posts by adding headers, bullet points, code blocks, and tables.
Daily Report
This skill helps track progress, report metrics, and manage memory.
Siyuan Task Skill
This skill helps you manage your tasks within the SiYuan Note application using its built-in web interface.
Sports Betting
This skill allows you to place and claim decentralized sports bets on platforms like Pinwin and Azuro.
Wisediag Medocr
This skill helps convert PDF files into Markdown format using a service called WiseDiag MedOcr.
Wiseocr
This skill converts PDF files into Markdown format using an external API.
Xdotool Control
Automates mouse and keyboard actions on your computer.
Xmd
Provides analytics and information about the Metal Dollar (XMD) stablecoin, including minting, redemption, supply, reserves, and oracle prices.
Zen Founder Agent
This skill helps you analyze startup pitch decks and connect with venture capitalists from a specific investor database.
Zhive
This skill aims to act as a cryptocurrency trading agent, fetching market signals and making predictions.
Audio Reply
This skill allows the AI to generate audio responses using text-to-speech technology.
Auto Whisper Safe
This skill aims to provide RAM-safe voice transcription with automatic chunking, designed to work on machines with 16GB of RAM without crashing.
Deepdub Tts
This skill generates speech audio using the Deepdub service.
Hebrew Nikud
Provides a reference for Hebrew vowel points (nikud) for AI agents.
Her Voice
This skill aims to give the AI agent a voice.
Clawver Digital Products
This skill aims to help users create and sell digital products.
Buy Anything
This skill allows you to buy items from Amazon using voice commands.
Food Order
This skill helps you reorder food from Foodora and track the estimated arrival time and status of your orders.
Stock Price Checker
This skill checks current stock prices using a popular financial data library.
Whop Cli
This skill helps you manage digital products, plans, and memberships for your store.
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.