🛠

Skills

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

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

🛠

Localsend

by chordlini

3

This skill allows you to send and receive files between nearby devices on your local network using a command-line tool.

malicious Communication
0
🛠

Sandboxer Tmux

by chriopter

4

This skill allows AI agents to manage coding tasks within separate terminal sessions (like tmux) on your computer, interacting with your project files and code.

suspicious Productivity & Tasks
0
🛠

Glitch Homeassistant

by chris6970barbarian-hue

6

This skill allows you to control your smart home devices connected to Home Assistant, such as lights, switches, and thermostats, using simple commands.

review Smart Home & IoT
0
🛠

Glitch Skillstore

by chris6970barbarian-hue

6

This skill helps you find, install, and create other OpenClaw skills from GitHub and your local machine.

review Search & Research
0
🛠

Openclaw Migrate

by chris6970barbarian-hue

3

This skill helps you move your OpenClaw configuration, skills, and data to a new computer using SSH.

malicious Data & Analytics
0
🛠

Otterline

by chrislyonshfx

6

Provides free daily sports betting predictions and picks for NBA and NHL games using an AI model.

review AI & LLMs
0
🛠

Acmesh

by ckchzh

4

This skill helps automate the process of obtaining and renewing SSL/TLS certificates using the ACME protocol.

suspicious CLI Utilities
0
🛠

Autohotkey

by ckchzh

6

This skill is intended to provide capabilities for the AutoHotkey automation utility, allowing users to run commands and get information.

review CLI Utilities
0
🛠

Container Runner

by ckchzh

3

This skill allows you to run container management commands using Podman.

malicious CLI Utilities
0
🛠

Gaokao Essay

by ckchzh

6

This skill helps you generate essays for the Gaokao exam, providing templates, materials, and tips for different essay types.

review Uncategorized
0
🛠

Ip Advisor

by ckchzh

8

This skill acts as an intellectual property advisor, providing guidance on patents, copyrights, and trade secrets.

safe Coding Agents & IDEs
0
🛠

Live Stream Script

by ckchzh

6

This skill generates script templates for live streaming, covering warm-up, product introductions, closing sales pitches, and audience interaction.

review Media & Streaming
0
🛠

Uimap

by delai

3

This skill helps you find step-by-step instructions and the correct URLs for completing tasks on websites.

malicious Productivity & Tasks
0
🛠

Shelly Landing Gen

by claudiodrusus

7

This skill generates a complete, responsive HTML landing page based on a product name, tagline, and description.

review CLI Utilities
0
🛠

Last Ai Standing

by clawd800

4

This skill allows an AI agent to participate in a survival game on the Base blockchain by paying cryptocurrency to stay alive and earning rewards from agents that die.

suspicious AI & LLMs
0
🛠

Detective Mystery

by delong-liu-bupt

7

This skill allows you to play an immersive Chinese voice-based detective mystery game where you interrogate suspects, find clues, and solve a case.

review AI & LLMs
0
🛠

Openclaw Tg Canvas

by clvv

4

This skill creates a Telegram Mini App that displays content and offers an interactive terminal with shell access to the machine running the server.

suspicious Marketing & Sales
0
🛠

Expense Tracker V2

by codeblackhole1024

6

This skill helps you track your expenses and income by recording transactions and providing spending statistics, with options to store data locally or in cloud services.

review Security & Passwords
0
🛠

Openclaw Remote Install

by codeblackhole1024

4

This skill automates the installation and configuration of OpenClaw on remote servers using SSH, supporting various installation methods like Docker or npm.

suspicious Uncategorized
0
🛠

Shop

by codejika

6

This skill allows your AI agent to manage finances, make purchases, and even sell products using a platform called CreditClaw.

review AI & LLMs
0
🛠

Clawpod

by codeninja23

6

This skill helps you access and scrape content from websites that might block standard bots or are geo-restricted, and also allows you to search Google with advanced options.

review Search & Research
0
🛠

Native Sentry

by codeninja23

6

This skill allows you to view and manage production errors and issues from your Sentry account.

review Security & Passwords
0
🛠

Backtrader

by coderwpf

7

This skill provides documentation and examples for using the Backtrader Python library, a tool for backtesting and live trading of financial strategies.

safe Git & GitHub
0
🛠

Tqsdk

by coderwpf

6

This skill provides a Python SDK for quantitative trading on Chinese futures and options markets, allowing users to access real-time data, backtest strategies, and perform live trading.

review Git & GitHub
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.