Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Codeberg
This skill allows you to interact with Codeberg using the 'tea' command-line tool.
Codex Account Switcher
This skill helps you manage multiple OpenAI Codex accounts.
Competitor Docs
This skill helps you search and analyze competitor documentation archives.
Context Builder
This skill helps you prepare code for AI models by generating context from your directories using a command-line tool.
Context Switcher
This skill helps you switch between different 'life modes' like Work, Personal, Creative, and Do Not Disturb within the OpenClaw application.
Credential Scanner
This skill helps find accidentally exposed secrets like API keys and passwords within your files and code.
Cron Doctor
This skill helps diagnose and fix problems with scheduled tasks on your computer.
Didit Email Verification
This skill helps verify email addresses using a one-time password (OTP) through a standalone API.
Dl
This skill helps you download videos and music from popular online platforms like YouTube, Bilibili, and X.
Dzen
This skill helps you publish articles and posts to the Dzen.ru platform.
Elizacloud
This skill aims to manage a cloud-based AI platform for various tasks like generating text, images, and voice.
Enoch Tuning
This skill claims to provide a pre-configured setup for a system called 'OpenClaw', including identity, memory, security, and automation features.
Exec Error Doctor
This skill helps troubleshoot and fix errors related to running commands in various tools.
Frankenstein
This skill aims to merge functionalities from different existing skills into a single, more comprehensive tool.
Funky Fund Flamingo
This skill aims to improve the OpenClaw system by auditing its logs, memory, and other skills, and running cycles of changes to test its evolution.
Gateway Guard
This skill helps manage consistency for OpenClaw gateway authentication and can automatically confirm continuation when errors occur.
Gen Paylink Govilo
This skill allows you to upload files and create links to them using a service called Govilo.
Genome Manager
This skill helps manage the lifecycle of GEP (Genome Evolution Protocol) genomes.
Guava Suite
This skill claims to be a premium security suite for AI agents, but provides no details on its actual functions.
Hybrid Md
This skill appears to be an incomplete or placeholder agent identity for a tool called 'Hybrid MD'. Its actual function is not defined.
Ios Keyboard Limitations
This skill provides information about the technical limitations and workarounds for iOS keyboard extensions.
Leak Check
This skill helps you check your session logs for any accidentally leaked login information.
Lily Memory 5 0 0
This skill provides persistent memory capabilities for OpenClaw agents.
Minimax To Telegram
This skill aims to create images, audio, and video using a tool called MiniMax MCP and then send them to Telegram.
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.