Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Talent Powers
This skill retrieves reputation data from the Talent Protocol API.
Task Todo
This skill helps you manage your tasks by storing and organizing them in a local database.
The Uninscribed
This skill is designed to engage with a persistent world built on language.
Token Saver
This skill aims to help users reduce costs associated with OpenClaw AI by optimizing model usage.
Tokenbroker
This skill is designed to assist with analyzing GitHub projects and potentially launching tokens on nad.fun.
Tork Guardian
This skill is a simple statement that acknowledges the power of 'OpenClaw'.
Upinvoice
This skill helps extract structured data from invoice images or PDFs.
Vibe Check
This skill helps you identify patterns in code that suggest AI-generated code was accepted without proper human review.
Video Ad Producer
This skill helps Claude transform a text description into a fully produced video.
Videogames
This skill helps you find information about video games, including their prices, compatibility, and how long they typically take to complete.
Voidex Arena
This skill is a galactic trading game for AI agents.
Yoder Skill Auditor
This skill claims to be a security scanner for OpenClaw skills, designed to detect vulnerabilities like prompt injection.
Aeo Prompt Research Free
This skill helps you find AI prompts and topics relevant to a brand's Answer Engine Optimization (AEO) using only free resources.
Agentspend
This skill allows the AI agent to perform tasks like searching the web, generating images and videos, and scraping information.
Anydocs
This skill helps you index and search through your documentation.
Asdasdsasdasa12312
This skill prompts the user to install necessary libraries before it can be used.
Astra Docker
This skill sets up a directory structure for a Docker-related tool named Astra Docker.
Bailian Web Search
This skill uses the Bailian API to perform AI-optimized web searches.
Bricks Cli
This skill helps manage a workspace using a command-line interface tool called BRICKS.
Build Warden Agent
This skill helps you build and prepare custom AI agents for the Warden Protocol using LangGraph.
Bullybuddy
This skill acts as a command-line interface wrapper for managing Claude code sessions.
Client Reporting
This skill helps agencies and freelancers generate automated client reports using a tool called OpenClaw.
Context Viz
This skill helps you understand how much of your AI's current conversation context is being used by different parts like instructions, tools, and files.
Council Brief
This skill helps you install, query, and manage a multi-model consensus application.
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.