Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Mh Obsidian
This skill helps automate tasks related to your Obsidian note-taking application using its command-line interface.
Qwen3 Tts Instruct
This skill provides access to Alibaba Cloud's Qwen Text-to-Speech service with different voice and mood options.
Rollbar
This skill helps you monitor and manage error tracking using the Rollbar service.
Skills 4
This skill provides instructions on how to use the coala-client command-line tool for interacting with LLMs, MCP servers, and other skills.
Slv Validator
This skill helps manage and deploy Solana validators using Ansible playbooks and Jinja2 templates.
Trilium
This skill helps automate tasks within the Trilium Notes application.
Valtec Tts
This skill provides offline Vietnamese text-to-speech functionality using the VITS2 model.
Vault
This skill helps you securely store your passwords locally using strong encryption.
Ace Music
This skill generates AI music using the ACE Music API.
Dxf To Image
This skill helps you convert DXF design files into common image formats like PNG, JPG, or SVG.
Immortal
This skill aims to help AI agents evaluate the health and performance of cryptocurrency resources.
Nanobanana Pro Fallback
This skill helps you generate and edit images using the Gemini Image API.
Openocr Skill
This skill helps you extract text from images, documents, and scanned PDFs.
Pr Generator
This skill generates QR codes from text, URLs, or images.
Superpower
This skill is designed to be activated when a user expresses frustration or has a task they want help with.
Apple Mail Search
This skill aims to help you quickly search your Apple Mail using SQLite on macOS.
Say
This skill uses your Mac's built-in text-to-speech feature to speak text aloud using natural-sounding voices.
Adhd Ssistant
This skill acts as an assistant to help users manage their lives in an ADHD-friendly way.
Arc Memory Pruner
This skill helps manage and reduce the size of your agent's memory files to prevent them from growing too large.
Gekko Strategist
This skill acts as an AI agent to help develop strategies for decentralized finance (DeFi).
Instagram Analyzer
Analyzes Instagram profiles and posts, including engagement metrics and view tracking.
Myfeed
This skill helps you manage your 'MyFeed' items and groups by interacting with its REST API.
Near Content Creator
This skill helps generate content related to the NEAR blockchain ecosystem, including market updates and tutorials.
Nostr Nak
This skill allows you to use the Nostr Army Knife (nak) command-line tool, which provides advanced features for interacting with the Nostr network.
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.