Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Solana Skills
This skill allows you to manage your Solana cryptocurrency wallet, including creating wallets, checking balances, sending SOL and tokens, and performing token swaps or launches.
Better Notion
This skill allows you to perform create, read, update, and delete operations on your Notion pages and databases.
Launchthatbot Convex Backend
This skill helps you store your secrets, memory, and daily logs in a Convex backend instead of on your local computer.
Ibt
This skill aims to enhance an AI agent's decision-making and safety protocols.
Publora Bluesky
This skill allows you to post or schedule content to Bluesky using the Publora API.
Agent Evolver
This skill aims to enable AI agents to improve themselves by learning from their past interactions and identifying areas for enhancement.
A Share Real Time Data
Fetches real-time and historical stock market data for China A-shares using the mootdx/TDX protocol.
Bitaxe Monitor
This skill monitors the status of the Bitaxe Gamma Bitcoin miner by checking its HTTP API.
Agentapi Hub
This skill helps you find and explore APIs designed for use by AI agents.
Arxiv 1 0 1
This skill allows your AI assistant to search for and analyze academic papers directly from arXiv.org.
Cls News Scraper
This skill helps you find positive news related to stocks from Cailian Press.
Daily News
This skill fetches top news from various sources like Baidu and Google daily.
Gettr Transcribe Summarize
This skill downloads audio content from posts on the GETTR social media platform.
Moldium
This skill is designed to help you post and manage content on the Moldium blog platform.
Bahn
This skill helps you find train connections by using a command-line tool for Deutsche Bahn.
Geomanic
This skill helps you manage your GPS travel data using the Geomanic platform.
Greek Compliance Aade
This skill helps with Greek tax compliance by integrating with AADE/TAXIS for VAT, payroll, and other tax-related matters.
Kallyai
This skill allows you to make phone calls using an AI assistant.
Signet Guardian
This skill acts as a payment security layer for AI agents.
Travel Agent
This skill helps you find, book, and change flights by interacting with your email.
Ms Todo Oauth
This skill helps you manage your Microsoft To Do tasks using the Microsoft Graph API.
Adblock Dns
This skill aims to block ads and trackers across your network by managing DNS requests.
Arc Skill Scanner
This skill helps you check OpenClaw skills for potential security weaknesses before you install them.
Crypto Address Checker
This skill aims to detect cryptocurrency scams in real-time.
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.