Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Dcg Guard
This skill acts as a guard to prevent the execution of dangerous shell commands.
Didit Proof Of Address
This skill integrates with the Didit Proof of Address API to help verify address documents.
Dj Set Ripper
This skill aims to help you download individual songs from DJ sets or mixes.
Embedded Review
This skill helps review embedded firmware code, focusing on memory safety, interrupts, and hardware checklists.
Fabrik Codek
This skill aims to create a personalized cognitive architecture for developers, focusing on profiling and competence modeling.
Hex Vetter
This skill is designed to perform hex auditing at a physical layer for other skills.
Imortalbrain
This skill provides a basic instruction for an AI agent related to OpenClaw.
Kagi Summarizer
This skill uses Kagi's service to summarize web pages or provided text.
Keychat
This skill helps you send and receive encrypted messages using Signal Protocol over Nostr relays.
Liblib Ai Gen
This skill helps you generate images and videos using the LiblibAI API.
Macos Notes
This skill allows you to create, read, search, and manage your notes within the macOS Notes application using AppleScript.
Macos Screenshot Telegram
This skill takes a screenshot of your macOS screen and sends it to a Telegram chat.
Magic Wormhole
This skill helps you securely share secrets using the magic-wormhole protocol.
Model Matrix
This skill helps manage and score models for OpenClaw, considering costs and policies.
Nate Jones Second Brain
This skill helps you set up and manage a personal knowledge system using Supabase and OpenRouter.
Ngrok Preview
This skill helps you create temporary web links to share local files or services, and then post those links to Telegram.
Ouyang
This skill helps an AI agent remember past conversations and information by storing it locally using a database.
People Strategy
This skill helps manage people relationships by storing information in a persistent graph database.
Pinchbench
This skill helps evaluate the performance of the OpenClaw agent using benchmarks.
Pr Code Reviewer
This skill automatically reviews pull requests on Bitbucket to detect errors.
Quiver
This skill retrieves alternative financial data, including information on congressional trading, lobbying, and government contracts, from Quiver Quantitative.
Remotion Excalidraw Tts
This skill generates a narrated video from an Excalidraw diagram using your computer's built-in text-to-speech functionality.
Ruby On Rails Gateway
This skill helps configure and operate a Ruby On Rails Agent Gateway integration.
Screenshot Skill
This skill captures screenshots on your Windows computer.
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.