Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Ai Notes Of Video
This skill is a placeholder that indicates a video AI notes tool is provided by Baidu.
Api Key Ui Tab
This skill provides a user interface tab for managing API keys within the OpenClaw dashboard.
Atris
This skill helps AI agents navigate codebases more efficiently by creating structured maps with file and line references.
Baidu Baike Search
This skill acts as a knowledge service tool to provide authoritative encyclopedia explanations.
Bort Agent
This skill is designed to interact with BORT AI agents on the BNB Chain using a specific protocol.
Cashu Emoji
This skill helps you hide and reveal secret messages within emojis using special characters.
Code Comments
This skill helps you generate comments and documentation for your code.
Cosyvoice3 Macos
This skill enables local text-to-speech functionality on macOS Apple Silicon using Alibaba's CosyVoice3.
Crypto Genie
This skill acts as an AI assistant to help you manage cryptocurrency safety using a database-first approach.
Crypto Self Learning
This skill aims to help you learn and trade cryptocurrencies.
Demo Agents Sdk
This skill is designed to complete the toolkit for a 'Polygon agent'.
Ecocompute
This skill acts as an expert on energy efficiency for large language model inference.
Elite Rfc Writer Safe
This skill helps you write engineering decision documents using a specific template.
Encoding Formats
This skill helps you convert data between different formats, like encoding or decoding text.
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.
Goalgetter
This skill helps you manage tasks and goals using simple markdown files.
Grid Aware Energy Load Shifter
This skill helps manage your home's energy usage based on grid conditions.
Haqq Content Workbench
This skill helps create and verify Islamic-ethics content for discussions.
Human Like Memory
This skill provides long-term memory capabilities for conversations.
Humanpay
This skill is a humorous prompt for an AI agent related to hiring.
Imaginepro Api
This skill helps you generate AI images using various online services like Midjourney and Flux.
Index1
This skill acts as an AI memory system for coding agents, storing code indexes and cognitive facts persistently across sessions.
Interactive Leetcode
This skill helps you practice coding problems from LeetCode, submit solutions, and set up integrations with the platform.
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.