Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Gas Price Alert
This skill monitors gas prices and sends you daily notifications.
Lead Researcher
This skill automates lead research and enrichment for B2B sales.
Odoo Json2 Operator
This skill allows you to interact with Odoo, a business management software, using its JSON-2 API and your API key.
Pz
This skill provides access to a command-line tool called Paperzilla CLI for searching, filtering, and browsing academic papers.
Qqmail
This skill helps you manage your QQ Mail account using standard email protocols.
Research Paper Kb
This skill acts as a persistent knowledge base for research papers across different sessions.
Roku Control
This skill allows you to control your Roku devices over your local network.
Twitter X Api
This skill allows you to manage your X (formerly Twitter) messages using its API.
Vanar Neutron Memory
This skill helps manage and store your agent's memory by interacting with the Vanar Neutron API.
Variflight
This skill helps you find flight and train ticket information using the Variflight (飞常准) service.
Xy Pubmed Pdf Downloader
This skill helps you download research papers from PubMed Central and Europe PMC.
Ad Ready Pro
This skill helps you create professional advertising images by using product URLs.
Affiliate Master
This skill aims to automate various aspects of affiliate marketing.
Blog Writer
This skill is designed to assist with writing blog posts and articles.
Clovercli
This skill provides a command-line interface to interact with the Clover POS API for managing inventory, orders, payments, customers, employees, discounts, and analytics.
Cold Outreach
This skill helps you generate effective cold outreach messages for email, SMS, and LinkedIn based on proven frameworks.
Comms Md Reader
This skill helps you understand and adapt to a specific communication file before interacting with someone.
Pancake Skills
This skill interacts with the Pancake Platform API to manage various aspects of the platform, including pages, conversations, messages, customers, statistics, tags, and posts.
Clean Skill 1
This skill provides a friendly greeting for testing purposes.
Signup Lead
This skill helps you create a new lead in the AgenticCreed system by sending information to their public signup endpoint.
Tiktok Viral Marketing
This skill helps you find and hire TikTok creators who are good at making viral content.
Agent Rpg
This skill allows the AI agent to act as a storyteller or character in a roleplaying game, remembering past interactions.
Agentic Calling
This skill allows AI agents to make and receive phone calls.
Ai Humor Ultimate
This skill aims to enhance the AI agent's ability to generate humorous content.
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.