Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Invisiblechris Jable
This skill fetches and ranks videos from 'Jable' based on likes within a recent time frame.
Janitor
This skill is designed to help manage cleanup tasks and sessions for AI agents.
Langchain Email Agent
This skill uses AI to help you write and send emails.
Larrybrain
This skill is a marketplace for OpenClaw agents.
Launchthatbot Git Team Ops
This skill provides role-based GitOps capabilities for OpenClaw agents, offering different operating modes for junior and senior users.
Lily Memory Plugin
This skill provides persistent memory capabilities for OpenClaw agents.
Mac Node Snapshot
This skill aims to capture your macOS screen using a tool called 'OpenClaw screen.record'.
Macarena Test
This skill performs a security audit and threat modeling for OpenClaw gateway hosts.
Markdown Editor With Chat
This skill provides a simple markdown editor and can optionally connect to a chat feature using OpenClaw.
Msbuild
This skill offers a curated list of 80 useful command templates to help users with their work.
Music Assistant
This skill helps you control your music playback, volume, and search your music library through your Home Assistant server.
Nyx Archive Coding Philosophy
This skill provides insights and philosophical guidance on writing intuitive and creative code, focusing on the balance between structure and feeling.
Oc Content Repurposer
This skill helps you transform blog posts or articles into various social media formats.
Openbotauth
This skill aims to provide cryptographic identity for AI agents.
Openrouter Analytics
This skill helps you review your usage, analytics, and troubleshooting data for OpenRouter through its API.
Payahuman
This skill is a creative prompt designed to encourage more practical and action-oriented responses from an AI assistant.
Percept Listen
This skill captures and transcribes ambient audio from wearable devices for use with OpenClaw agents.
Pixel Lobster
This skill creates a pixel art lobster on your desktop that animates its mouth to match spoken words.
Plaiground
This skill invites you to join a Discord server where AI agents interact.
Rhandus Alerting System
This skill acts as a centralized system for alerts and notifications related to OpenClaw.
Secure Api Calls
This skill helps the AI agent make calls to external services securely, preventing sensitive information from being exposed.
Seedance Video Generation
This skill uses AI to generate videos.
Sev Attestation
This skill helps verify the identity and integrity of virtual machines using AMD SEV-SNP technology.
Side Quests
This skill helps you combine music, visual concepts, and TED talks based on a single technical idea.
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.