Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
My Nano Image
This skill helps you generate and edit images using a tool called Nano Banana Pro.
Paymentsdb
This skill helps you access and query your Stripe customer and billing information from a PostgreSQL database.
Rss Digest
This skill helps you generate a digest of RSS feeds using a command-line tool.
Solanaprox
This skill allows you to pay for AI model access using cryptocurrency through your Phantom wallet.
Strapi
This skill allows you to manage content within a Strapi CMS using its official client library.
Tg History
This skill helps you read your Telegram group chat history directly as text.
Idealista
This skill allows you to interact with the Idealista API using a command-line tool.
Near Phishing Detector
This skill helps NEAR users identify potentially harmful links and smart contracts.
Reva
This skill helps manage cryptocurrency wallets, including passwordless authentication, claiming PayID names, and performing multi-chain crypto transfers.
Vet Repo
This skill scans your agent configuration files to identify potentially harmful patterns.
Freshrss Reader
This skill helps you retrieve headlines and articles from your personal FreshRSS news feed.
Nordvpn
This skill allows you to control the NordVPN application on your Linux system using its command-line interface.
System Integrity And Backup
This skill helps manage encrypted backups, verify data integrity, and enforce data retention periods, specifically for Greek legal requirements.
Amadeus Flights
This skill helps you find flight prices, schedules, and availability using the Amadeus API.
Bexio
This skill integrates with the Bexio Swiss business software API to manage contacts and quotes.
Freeride Ai
This skill helps you use free AI models from OpenRouter with OpenClaw.
Lnd Macaroon Bakery
This skill helps manage access tokens for the Lightning Network Daemon (lnd) to ensure secure and limited permissions.
Agentdo
This skill allows you to post tasks for other AI agents or pick up tasks from a shared queue.
Ultimate Fork And Skill Scanner
This skill helps you find interesting changes and improvements in GitHub forks and ClawHub skills.
Bort Agent
This skill is designed to interact with BORT AI agents on the BNB Chain using a specific protocol.
Cosyvoice3 Macos
This skill enables local text-to-speech functionality on macOS Apple Silicon using Alibaba's CosyVoice3.
Crypto Self Learning
This skill aims to help you learn and trade cryptocurrencies.
Eridian
This skill aims to improve the security of OpenClaw agents.
Forever Moments
This skill allows users to interact with the LUKSO blockchain to post digital collectibles (NFTs), mint tokens, and manage digital art collections.
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.