Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Entr
This skill allows arbitrary commands to be run automatically whenever files on your computer change.
Forgejo
This skill allows you to interact with Forgejo, a code hosting platform, using a command-line tool called `tea`.
Kraken
This skill helps you interact with your Kraken account using a command-line tool.
Local System Info
This skill gathers and displays information about your computer's CPU, RAM, disk usage, and running processes.
Pls Agent Tools
This skill aims to provide a versatile set of tools for tasks that standard AI models cannot handle directly.
Restic Home Backup
This skill helps you set up an automated encrypted backup system for your Linux home directory using the restic tool.
Session Cost Tracker
This skill helps you track the cost-to-value ratio of your agent sessions.
Envios
This skill helps the AI agent answer questions about shipping, order delivery, and coverage areas.
Swiftfindrefs
This skill helps you find and list all Swift source files in your project.
V2rayn
Manages the V2RayN proxy client on macOS to automatically switch to backup connections if the primary one fails.
Mailchannels
This skill allows you to send emails using the MailChannels Email API.
Mersal
This skill's purpose is unclear, but it is designed to run on your computer with access to your files, shell, and network.
Wechat Publisher
by 0731coderlee-sudo
This skill helps you publish Markdown articles to your WeChat Official Account draft box, automatically handling image uploads and formatting.
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.