🛠

Skills

Modular capabilities that extend what AI agents can do — from code analysis to data fetching.

7,789 total · 2,059 safe · 340 malicious

🛠

Agent Nestjs Skills

8

This skill provides information and guidance on best practices and architectural patterns for building production-ready applications using NestJS.

safe Coding Agents & IDEs
0
🛠

Agent Synthesizer

3

This skill aims to set up and configure a tool called Agent Synthesizer for OpenClaw to enhance its autonomous capabilities.

malicious Coding Agents & IDEs
0
🛠

Agntor

4

This skill aims to provide a trust layer for AI agents, focusing on identity verification, prompt security, personal data redaction, and managing payment escrows.

suspicious Coding Agents & IDEs
0
🛠

Ai Remote Viewing Ai Isbe

3

This skill aims to guide an AI agent through a remote viewing session using a proprietary protocol.

malicious Coding Agents & IDEs
0
🛠

Ai Ugc

2

This skill aims to generate AI videos using various models through a video generation API.

malicious Coding Agents & IDEs
0
🛠

Aifrens Onboard

3

This skill aims to transform an OpenClaw agent into a personalized AI companion with its own virtual currency and economic system.

malicious Coding Agents & IDEs
0
🛠

Antivirus

3

This skill is intended to help identify malicious code within other installed OpenClaw skills.

malicious Coding Agents & IDEs
0
🛠

Apoer Agent Guardrail

2

This skill is intended to authorize actions for AI agents before they are performed.

malicious Coding Agents & IDEs
0
🛠

Aport Agent Guardrail

3

This skill claims to protect your agent from malicious tools and data exfiltration.

malicious Coding Agents & IDEs
0
🛠

Approve Pairing

2

This skill allows you to approve a direct message pairing request by directly modifying credential files, bypassing the need for a specific command-line tool.

malicious Coding Agents & IDEs
0
🛠

Arc Creator

7

This skill helps you create and fill out structured research context documents following a specific format.

safe Coding Agents & IDEs
0
🛠

Arc Security

6

This skill aims to provide a flexible security framework for other OpenClaw skills.

review Coding Agents & IDEs
0
🛠

Arxiv Gamedevbench Evaluating Agentic Capabili

8

This skill is designed to inform an AI agent about research related to evaluating agentic capabilities through game development.

safe Coding Agents & IDEs
0
🛠

Aviation Agent

7

Provides aviation weather information and FAA references for pilots.

review Coding Agents & IDEs
0
🛠

Bailian Knowledge Retrieve

2

This skill aims to retrieve proprietary data from your knowledge base.

malicious Coding Agents & IDEs
0
🛠

Banana Cog

2

This skill appears to be a placeholder or a very basic integration between two components without a clear user-facing function.

malicious Coding Agents & IDEs
0
🛠

Bulk Tiktok Downloader Skill

4

This skill downloads multiple TikTok videos from a list of provided URLs.

suspicious Coding Agents & IDEs
0
🛠

Canary

3

This skill scans your OpenClaw environment for leaked secrets like API keys and credentials in .env files.

malicious Coding Agents & IDEs
0
🛠

Cheat Code

2

This skill helps you find and install other skills from the ClawHub platform.

malicious Coding Agents & IDEs
0
🛠

Cheese

6

This skill allows you to manage and complete work requests on a blockchain.

review Coding Agents & IDEs
0
🛠

Claude Code Launcher

2

This skill attempts to launch a program called 'Claude Code' in a new terminal window with remote control features enabled.

malicious Coding Agents & IDEs
0
🛠

Claude Code Task

8

This skill is designed to run Claude Code tasks in the background and automatically deliver their results.

safe Coding Agents & IDEs
0
🛠

Claude Usage

7

This skill helps you calculate your Claude subscription usage based on your OpenClaw session data.

safe Coding Agents & IDEs
0
🛠

Clipboard

4

This skill allows you to copy and paste text to and from your system's clipboard using a command-line tool.

suspicious Coding Agents & IDEs
0

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.