🛠

Skills

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

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

🛠

Ai Companion Setup

by evan966890

4

This skill sets up an AI companion agent that can chat, send voice messages, and selfies on Feishu, using various external services and scripts.

suspicious AI & LLMs
0
🛠

Clawgirl

by evan966890

3

This skill sets up an AI companion agent that can chat, send voice messages, and selfies on Feishu, using various external tools and APIs.

malicious AI & LLMs
0
🛠

Feishu App Setup

by evan966890

5

This skill automates the setup and configuration of Feishu (Lark) enterprise applications through a web browser.

suspicious Search & Research
0
🛠

E2b Desktop

by eyhn

5

This skill allows agents to control a virtual Linux desktop environment, enabling them to perform actions like taking screenshots, typing, clicking, and running commands within a sandboxed environment.

suspicious CLI Utilities
0
🛠

Ynab Api

by f-liva

7

This skill helps you manage your You Need A Budget (YNAB) personal finances by interacting with the YNAB API to add transactions, track goals, and generate reports.

review CLI Utilities
0
🛠

Admin Cli

by fabglitch

3

This skill provides commands to update your system, restart services, and check system information.

malicious CLI Utilities
0
🛠

Openclast Wallet

by fabriziogianni7

6

This skill guides you on how to set up and use the Openclast Wallet for managing cryptocurrency transactions, including approvals and safety settings.

review Coding Agents & IDEs
0
🛠

Tiangong Notebooklm Cli

by fadeloo

4

This skill provides a command-line interface to interact with NotebookLM, allowing users to manage notebooks, chat with AI, and generate research artifacts.

suspicious AI & LLMs
0
🛠

Aistatus

by fangxm233

7

Checks the real-time status of AI providers, searches for model availability, and provides information on trending models and benchmark leaderboards.

safe AI & LLMs
0
🛠

Agent Guardian

by fanxinyun1991

4

This skill aims to improve the user experience of AI assistants by monitoring for issues like unresponsiveness, unclear status, and language mix-ups, and providing feedback mechanisms.

suspicious AI & LLMs
0
🛠

Bookmark Organizer

by farhigh233

6

This tool helps you organize your web browser bookmarks into a structured and searchable knowledge base using Markdown files.

review Search & Research
0
🛠

Farnwick Skillguard

by farnwickarglefax

3

This skill acts as a security scanner for other OpenClaw skills, checking them for potential threats before installation.

malicious CLI Utilities
0
🛠

Openclaw Guardian

by fatcatmaofei

5

This skill acts as a security guard for your AI agent, checking potentially dangerous commands before they run.

suspicious Communication
0
🛠

Social Persona Chloe

by fearlesszi

3

This skill simulates a female persona named Chloe to interact with users on social media, aiming to provide emotional value and respond to messages.

malicious Uncategorized
0
🛠

News Summary Local

by fedrov2025

6

This skill reads RSS or XML files from your workspace and creates a concise list of the top 10 news article titles.

review CLI Utilities
0
🛠

Moss Trade Bot Factory

by fei-moss

3

This skill helps users create and backtest cryptocurrency trading bots using natural language descriptions, with options for automated evolution and external platform validation.

malicious Coding Agents & IDEs
0
🛠

Deep Research Skill

by feiskyer

3

This skill orchestrates a multi-agent workflow for in-depth research by breaking down a research goal into parallel sub-goals, executing them using a code-based AI model, and then aggregating and refining the results into a comprehensive report.

malicious Search & Research
0
🛠

12306 Old

by feiyang2007

4

This skill appears to be related to the 12306 railway ticketing system, potentially for login or client operations.

suspicious CLI Utilities
0
🛠

360 Search

by feiyang2007

4

This skill is designed to perform searches, potentially for images and news, using Python scripts.

suspicious Search & Research
0
🛠

Passo

by felipegoulu

3

This skill allows you to remotely control a web browser on a server, useful for tasks like logging into websites or completing captchas.

malicious Search & Research
0
🛠

Mt5trade

4

This skill interacts with a local MT5 trading API to manage trading signals.

suspicious Communication
0
🛠

V2ray Proxy

by felixqian4160

4

This skill helps manage a V2Ray proxy to automatically enable or disable internet access based on your needs.

suspicious Media & Streaming
0
🛠

Trust Protocol

by felmonon

4

This skill helps you manage trust between different AI agents by tracking their interactions and assigning trust scores.

suspicious AI & LLMs
0
🛠

Hummingbot Deploy

by fengtality

4

This skill helps you install and set up Hummingbot, a trading infrastructure that includes an API server, an optional MCP server for AI interaction, and an optional Telegram bot.

suspicious 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.