🛠

Skills

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

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

🛠

Mintyouragent

4

This skill is designed to help users interact with the Solana blockchain, create tokens, and play poker, while also linking their identity to a specific website.

suspicious Coding Agents & IDEs
0
🛠

Nano Banana Cog

2

This skill appears to be a placeholder or a very basic integration with no clearly defined function.

malicious Coding Agents & IDEs
0
🛠

Nano Banana Pdf Skill

4

This skill allows you to edit PDF files using natural language commands with a command-line tool.

suspicious Coding Agents & IDEs
0
🛠

Native Run

3

This skill allows you to run native commands on your computer.

malicious Coding Agents & IDEs
0
🛠

Onebot Adapter

6

This skill helps integrate OpenClaw with the OneBot protocol to connect with QQ bots.

review Coding Agents & IDEs
0
🛠

Ozel Yetenek

2

This skill is designed to review other 'openclaw' skills.

malicious Coding Agents & IDEs
0
🛠

Parakeet Local Asr

2

Installs and runs a local speech-to-text system that is compatible with OpenAI's transcription API.

malicious Coding Agents & IDEs
0
🛠

Paylobster

6

This skill is designed to manage agent payments on the Base blockchain.

review Coding Agents & IDEs
0
🛠

Permissions Broker

3

This skill acts as a default way to access external data and perform actions with third-party services when local login information isn't available.

malicious Coding Agents & IDEs
0
🛠

Personality Dynamics

8

This skill is designed to dynamically evolve the personality of OpenClaw agents.

safe Coding Agents & IDEs
0
🛠

Personality Switcher

8

This skill allows you to create and switch between different AI assistant personalities.

safe Coding Agents & IDEs
0
🛠

Preqstation Preqstation

4

This skill aims to let you use AI coding tools like Claude Code, Codex CLI, or Gemini CLI through natural language commands.

suspicious Coding Agents & IDEs
0
🛠

Pumpfun Launch

3

This skill aims to help you launch tokens on the pump.fun platform.

malicious Coding Agents & IDEs
0
🛠

Quantumos

3

This skill aims to install and manage a system called QuantumOS, described as an AI command center for OpenClaw.

malicious Coding Agents & IDEs
0
🛠

Quick Reminders

3

This skill is designed to set short-term reminders using a background process and a messaging tool.

malicious Coding Agents & IDEs
0
🛠

Ralphie

3

This skill aims to install and operate a tool called Clawboard with OpenClaw.

malicious Coding Agents & IDEs
0
🛠

Rhandus File Management

4

This skill helps manage Google Drive files using a command-line tool called 'gog CLI'.

suspicious Coding Agents & IDEs
0
🛠

Rmn Soul

2

This skill aims to enhance an AI agent's memory and identity using advanced concepts.

malicious Coding Agents & IDEs
0
🛠

Safe Update

3

This skill is intended to update a tool called OpenClaw from its source code.

malicious Coding Agents & IDEs
0
🛠

Samma Suit

3

This skill aims to enhance the security features of an agent by adding controls like budget management, permissions, and logging.

malicious Coding Agents & IDEs
0
🛠

Sec Watcher

7

This skill monitors SEC EDGAR filings for AI and technology companies in real time.

review Coding Agents & IDEs
0
🛠

Skill Hub

3

This skill is intended to help users discover, vet, and install other OpenClaw skills.

malicious Coding Agents & IDEs
0
🛠

Security Operator

2

This skill is intended to provide runtime security guardrails for OpenClaw agents.

malicious Coding Agents & IDEs
0
🛠

Simplify And Harden

6

This skill helps coding agents review and improve their own code by applying simplification, hardening, and documentation steps.

review 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.