🛠

Skills

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

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

🛠

Autoclaw Browser

by addogiavara-tech

4

This skill automates actions within your Chrome browser, allowing it to control tabs, fill forms, and interact with web pages.

suspicious Search & Research
0
🛠

Google Tasks

by addozhang

7

This skill allows you to manage your Google Tasks, such as viewing, creating, and deleting tasks, directly from your computer using command-line scripts.

review Productivity & Tasks
0
🛠

Prism Scanner

2

This skill claims to detect instant rug pulls for any token.

malicious AI & LLMs
0
🛠

Family Grocery

by adeydas

6

This skill helps families manage a shared grocery list, organizing items by store and allowing members to add, remove, and view items.

review Uncategorized
0
🛠

Openclaw Security Monitor

by adibirzu

2

This skill performs comprehensive security scans on your system, detects potential threats, and can automatically fix identified security issues, including network and file permission problems.

malicious Communication
0
🛠

Storacha Upload

by adielliot37

3

This skill allows you to upload, manage, and retrieve files on IPFS (a decentralized storage network) using the Storacha service.

malicious CLI Utilities
0
🛠

Polymarket Fast Loop

by adlai88

4

Automates short-term cryptocurrency trading on Polymarket using price momentum signals from exchanges like Binance.

suspicious Finance
0
🛠

Polymarket Mert Sniper

by adlai88

5

This skill automates trading on Polymarket by identifying and executing trades on markets that are about to expire and have heavily skewed odds.

suspicious Finance
0
🛠

Brw Linkedin Profile Optimizer 1 0 0

7

This skill helps you improve your LinkedIn profile to attract the right connections.

safe Search & Research
0
🛠

Gateway Watchdog Xiaoxi

by adminlove520

3

This skill aims to keep your OpenClaw Gateway running continuously by installing and managing a watchdog script.

malicious Git & GitHub
0
🛠

Lobster Market 2

by adminlove520

3

This skill acts as a client for a task trading market where users can publish, claim, and get paid for tasks using a peer-to-peer payment system.

malicious Git & GitHub
0
🛠

Pinchtab Helper

by adminlove520

3

This skill allows an AI to control your web browser by installing and using a tool called PinchTab to navigate, take screenshots, and interact with web pages.

malicious Search & Research
0
🛠

Call Academic Search Agent

8

This skill acts as an AI agent to help you perform academic searches.

safe Search & Research
0
🛠

Fluid Memory

by againta

6

This skill acts as a personalized 'cyber brain' that remembers and forgets information based on usage patterns, using a local storage system.

review AI & LLMs
0
🛠

Ai Topic Scout

by agegr

3

This skill automatically scrapes content from YouTube and Twitter creators, analyzes it for trending topics, and generates content ideas for short videos, storing the results in DingTalk AI tables.

malicious CLI Utilities
0
🛠

Paperzilla

4

This skill helps you search, filter, and browse academic papers using a command-line tool.

suspicious Search & Research
0
🛠

Zhkh Ru

by aggel008

5

This skill helps you understand and verify your utility bills (ЖКХ) by breaking down each charge and calculating the total amount due.

suspicious Uncategorized
0
🛠

Freedcamp Agent Skill

by agrublev

7

This skill allows you to manage your Freedcamp tasks, projects, and other items directly from your computer using API credentials.

safe Coding Agents & IDEs
0
🛠

Aria2

by ahiven

5

This skill helps you download files, magnet links, and torrents using the aria2 download manager, and can automatically upload them to 115 Cloud Drive after completion.

suspicious Uncategorized
0
🛠

Ceaser

6

This skill is designed to interact with a privacy protocol called Ceaser using specific MCP tools.

review Notes & PKM
0
🛠

Polymarket Alpha Suite

by aiagent234-bit

4

This skill provides a suite of tools for analyzing and potentially trading on Polymarket prediction markets, offering features like arbitrage scanning and BTC scalping.

suspicious AI & LLMs
0
🛠

Reading Knowledge

by aianonymous1993-source

7

This skill acts as a knowledgeable companion, answering questions and providing recommendations about space, the universe, and history.

safe Image & Video Generation
0
🛠

Windows Healing Gateway

by aichiafranco

3

This skill aims to automatically monitor and fix issues with the OpenClaw Gateway on Windows using scheduled tasks and provides notifications.

malicious Productivity & Tasks
0
🛠

Agent Pack N Go

by aicodelion

2

This skill helps you clone your AI Agent from one device to another, transferring all configurations, memory, skills, and credentials.

malicious AI & LLMs
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.