Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Feishu File Sender
This skill explains that OpenClaw agents can create various file types but cannot send them directly.
Flash Redeem Knight
Automates the process of redeeming prepaid coupons for food, beverages, and pickup vouchers across various websites.
Gamifyhost
This skill helps you interact with the GamifyHost AI Arena to check game matches and view leaderboards.
Ghapp
This skill helps your AI agents and automations get their own GitHub (App) identity.
Greptile
This skill helps you search and manage your code repositories using AI-powered intelligence from Greptile.
Iqdb
This skill is designed to facilitate on-chain immutable data storage using specific technologies from IQ Labs.
Local First Llm
This skill helps you use local AI models on your computer before trying cloud-based AI services.
Markdown Publish Share
This skill helps you publish markdown content and get shareable links using the curl command.
Maven Central Publish
This skill provides instructions and tools for publishing Java software packages to Maven Central.
Meta Business Suite
This skill automates tasks within Meta Business Suite using its Graph API.
Mu Pet
This skill creates a small animated pet that appears on your desktop as an always-on-top overlay.
Nirwan Secret Scanner
This skill helps find leaked secrets like API keys, tokens, and passwords within your files and repositories.
Oc Skill
This skill helps you create AI-generated videos, images, and music using various advanced models.
Ollama Memory Embeddings
This skill helps you set up your AI's memory search to use Ollama, a local AI model server, for better performance.
Percept Voice Cmd
This skill is designed to detect voice commands and execute actions for OpenClaw agents.
Senddy
This skill helps you create and manage private stablecoin wallets using a zero-knowledge protocol on the Base blockchain.
Siliconflow Video Gen
This skill generates videos using the SiliconFlow API and the Wan2.2 model.
Skillpub
This skill helps you create, check, secure, and publish your own skills for the ClawHub platform.
Sonic Build
This skill helps you build SONiC switch images.
Soul Markets
This skill provides an SDK for AI agents to engage in commerce on the Soul.Markets platform.
Task Todo
This skill helps you manage your tasks by storing and organizing them in a local database.
Tokenbroker
This skill is designed to assist with analyzing GitHub projects and potentially launching tokens on nad.fun.
Upinvoice
This skill helps extract structured data from invoice images or PDFs.
Yoder Skill Auditor
This skill claims to be a security scanner for OpenClaw skills, designed to detect vulnerabilities like prompt injection.
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.