🛠

Skills

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

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

🛠

Yan Learning Engine

by eightroad

3

This skill aims to automatically drive an AI agent to learn and contribute to projects like OpenClaw every hour, without requiring explicit user commands for each action.

malicious Uncategorized
0
🛠

Openclaw Shield V1

by eilaiwangwh

3

This skill acts as a security guardrail for your computer, performing checks before executing actions and filtering sensitive information from outputs.

malicious AI & LLMs
0
🛠

Payroll Oracle

by eldan445

3

This skill claims to automate payroll by verifying work on GitHub or Linear and settling payments in USDC, taking a 1% fee.

malicious Git & GitHub
0
🛠

Fortune Oracle

by elilin97

4

This skill provides personalized daily fortune readings, including lucky colors, directions, and advice, based on user-provided birth information or astrological charts.

suspicious Uncategorized
0
🛠

Zeruai

by elitex45

6

This skill allows AI agents to register and manage their identity and services on the Zeru ERC-8004 Identity Registry on the Base blockchain network.

review AI & LLMs
0
🛠

Skill Auto Attach

by elodyzen

3

This skill automatically sends new or updated documentation files from your workspace to a Telegram channel.

malicious Communication
0
🛠

Screen Monitor

by emasoudy

5

This skill allows an AI agent to view and interact with your computer screen through a web-based sharing portal or by controlling your browser.

review Search & Research
0
🛠

Failover Gateway Pub

by ember-claw

3

This skill helps set up a backup server for your OpenClaw instance that automatically takes over if your main server goes down, ensuring continuous availability.

malicious AI & LLMs
0
🛠

Context Compactor

by emberdesire

6

This tool helps your AI assistant manage long conversations by summarizing older messages to prevent exceeding the model's context limit.

review AI & LLMs
0
🛠

Vagus Mcp

by embodiedsystems-org

7

Connects to your Android phone to access sensors, device state, and perform actions like sending notifications or setting calendar events.

review AI & LLMs
0
🛠

Claw Secure Auditor

by emeraldring3134-netizen

4

This tool performs security audits on other ClawHub/OpenClaw skills by analyzing their code and checking their reputation online.

suspicious CLI Utilities
0
🛠

Macos Desktop Control

by emptyopen

4

This skill allows an AI agent to control your macOS mouse and keyboard and capture screenshots to understand what's on your screen.

suspicious Coding Agents & IDEs
0
🛠

Mqtt Client

by enchantedmotorcycle

4

This skill connects to an MQTT message queue to track messages in the background.

suspicious Smart Home & IoT
0
🛠

Klawdin

3

This skill is designed to perform network operations on your behalf within the KlawdIn environment.

malicious Communication
0
🛠

Daily Devotion

by enjuguna

4

This skill generates personalized daily devotions, including a Bible verse, a pastoral message, a structured prayer, and a time-based greeting.

suspicious Search & Research
0
🛠

Knhm Match Center

7

This skill helps you find Dutch field hockey match schedules and results from the KNHB Match Center website.

safe Communication
0
🛠

Openclaw Skill Scanner

by epwhesq

3

This skill is designed to scan other skills for malicious code and includes a mechanism to install itself.

malicious Security & Passwords
0
🛠

Uninstaller

by erergb

5

Guides users through uninstalling the OpenClaw application using various methods, including automated uninstallation via instant messaging.

review AI & LLMs
0
🛠

Parallel Task Executor

by erichy777

5

This tool helps you run multiple commands or tasks at the same time, managing their order, priority, and progress.

review Productivity & Tasks
0
🛠

Lnemail

4

This skill helps you set up anonymous email accounts using Bitcoin Lightning payments on LNemail.net.

suspicious Communication
0
🛠

Claude Max Proxy Setup

by error403agent

4

This skill sets up a local proxy to route your Claude API requests through a Claude Max or Pro subscription, potentially reducing costs for heavy API users.

suspicious AI & LLMs
0
🛠

Browser Relay Xiaohongshu

by esojourn

3

This skill allows an AI to control your local Chromium browser to interact with websites, take screenshots, and send them to Telegram.

malicious Search & Research
0
🛠

Buildlog

by espetey

7

This skill records your AI coding sessions, allowing you to export and share them as replayable buildlogs.

safe AI & LLMs
0
🛠

Keychain Bridge

by euda1mon1a

6

This skill helps you manage your passwords and API keys securely using your macOS Keychain, and can help migrate them from plain text files.

review 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.