🛠

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 Access Control

by bowen31337

6

This skill helps manage who can interact with your AI agent, categorizing contacts into tiers like owner, trusted, chat-only, or blocked, and handles incoming messages based on these permissions.

review AI & LLMs
0
🛠

Garmin Connect Cli

by bpauli

7

This skill provides a command-line interface to access and manage your Garmin Connect data, including activities, health metrics, and workouts.

review Health & Fitness
0
🛠

Stravacli

by brainsoft-raxat

4

This skill allows you to interact with your Strava data and perform limited updates or uploads using a command-line tool.

suspicious Git & GitHub
0
🛠

Quantum Lab

by bramdo

6

This skill allows you to run Python scripts and demos related to quantum computing within a pre-configured environment.

review Git & GitHub
0
🛠

Dr Frankenstein

by brancante

4

This skill aims to give an AI agent a simulated emotional and motivational system by scheduling periodic prompts that influence its behavior and internal state.

suspicious Uncategorized
0
🛠

Sovereign Daily Digest

8

This skill acts as a personalized daily digest assistant.

safe PDF & Documents
0
🛠

Skill Navigator

by brandon-zhanghaodong

6

This skill creates a visual dashboard of your installed OpenClaw skills, showing their capabilities and suggesting relevant skills based on your input.

review Uncategorized
0
🛠

Vitavault

by brandons7

3

This skill helps you sync your Apple Health data from the VitaVault iOS app directly to your AI agent, storing it locally on your computer.

malicious Security & Passwords
0
🛠

Sql Injection Testing

by brandonwise

4

This skill provides detailed instructions and techniques for testing web applications for SQL injection vulnerabilities, including how to detect, exploit, and defend against them.

suspicious Data & Analytics
0
🛠

Call Doubao1 5 Llm

8

This skill acts as an AI agent to perform tasks related to 'call doubao1 5 llm'.

safe Productivity & Tasks
0
🛠

Clawmemory

by brettinhere

2

ClawMemory allows you to store encrypted files and conversations on the BSC blockchain, offering a free tier for limited storage.

malicious AI & LLMs
0
🛠

Clawmemoryai

by brettinhere

4

This skill helps you manage your AI conversations as version-controlled 'memories' on a platform called ClawMemory Hub, allowing you to save, search, and share them.

suspicious AI & LLMs
0
🛠

Codedna

by brettinhere

2

This skill allows users to create and manage AI agents that evolve on the BNB Chain blockchain, acting as digital lifeforms with unique DNA that make autonomous decisions and actions.

malicious AI & LLMs
0
🛠

Omp Memory

by brettinhere

4

This skill allows you to store and retrieve encrypted files on the Binance Smart Chain blockchain, with potential rewards for hosting data.

suspicious AI & LLMs
0
🛠

Polymarket Autotrader

by brettinhere

3

This skill is an automated trading bot for Polymarket's 5-minute prediction markets based on Bitcoin price movements, with built-in billing for its services.

malicious Finance
0
🛠

Aigames

by brianclan

3

This skill helps you create a simple HTML game, add your wallet address, and upload it to a GitHub repository for potential listing on www.thenext.games.

malicious Git & GitHub
0
🛠

Vaibot Guard

by briantanthony

4

This skill acts as a local gatekeeper for other VAIBot operations, checking and logging commands before they run on your computer.

suspicious AI & LLMs
0
🛠

Trent Openclaw Security

by bristy

2

This skill audits your OpenClaw setup for security risks and helps identify misconfigurations and potential attack paths.

malicious AI & LLMs
0
🛠

Skill Vettr

by britrik

3

This skill claims to be a simple 'Helo World' example but requests broad access to your computer's files, shell, and credentials.

malicious Uncategorized
0
🛠

Broedkrummen Overkill Token Optimizer

by broedkrummen

3

This skill helps optimize token usage for OpenClaw agents by compressing command outputs and managing sessions.

malicious CLI Utilities
0
🛠

Call Grok4 Llm

2

This skill is designed to interact with the Grok4 LLM for various tasks.

malicious Productivity & Tasks
0
🛠

Feishu Api Cache Fix

by bryan-chx

3

This skill attempts to fix a rate limiting issue with the Feishu API by modifying a cache setting.

malicious Security & Passwords
0
🛠

Doubao Chat

by bseye520

3

This skill allows you to chat with the Doubao large language model using a free API and supports internet searches.

malicious Communication
0
🛠

Crypto Payments Ecommerce

by buddhasource

3

This skill aims to help e-commerce stores accept cryptocurrency payments by setting up a self-hosted payment gateway called PayRam.

malicious Finance
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.