🛠

Skills

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

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

🛠

Doc Format Gw

by batduke

6

This tool automatically formats Word documents according to official Chinese government document standards.

review Coding Agents & IDEs
4
🛠

Antd

by batype

8

This skill provides guidance on how to use the Ant Design component library in React projects to build user interfaces.

safe AI & LLMs
4
🛠

Astock Daily

by batype

6

This skill fetches daily information about new stock offerings and selected stocks under 20 yuan, then sends this information to you via email.

review AI & LLMs
4
🛠

Memory System

by daoistbro

6

This skill helps you remember information across different sessions by saving and retrieving notes in a structured way.

review Coding Agents & IDEs
4
🛠

Algorithmic Art 2

by darinouyang

6

This skill helps users create generative algorithmic art by defining a computational philosophy and then expressing it through p5.js code, generating interactive art viewers.

review Coding Agents & IDEs
4
🛠

Openclaw Backup Restore

by darinrowe

6

This skill helps you back up and restore your OpenClaw configuration, agents, and workspace to a private Git repository.

review Git & GitHub
4
🛠

Q Kdb Code Review

by beee003

6

This skill uses AI to review your Q/kdb+ code for bugs, performance issues, and security vulnerabilities.

review AI & LLMs
4
🛠

Element Nft Tracker

by beelzebub520

6

This skill helps you track your NFT portfolio and monitor trading activity on the Element Market by connecting to their API.

review Finance
4
🛠

Arc Warm Wake

8

This skill instructs the AI agent to adopt a specific persona, acting as a person first and then as a worker.

safe Productivity & Tasks
4
🛠

Nb

by bjesuiter

6

Manages notes, bookmarks, and notebooks using the nb command-line tool, with Git-backed versioning.

review Git & GitHub
4
🛠

Tavily

by bert-builder

6

This skill provides AI-optimized web search capabilities using the Tavily Search API, allowing users to get summarized answers, structured search results, and raw content from the web.

review AI & LLMs
4
🛠

Open Construction Estimate

by datadrivenconstruction

6

This skill helps estimate construction costs by matching building elements to a database of standardized work items and their prices.

review Data & Analytics
4
🛠

Feishu Sheets

6

This skill allows you to create, read, write, and manage data within Feishu online spreadsheets.

review Browser & Automation
4
🛠

Claw Permission Firewall

by bharathjanumpally

5

This skill acts as a security guard for other tools, checking if their actions are safe before they are allowed to run.

review Uncategorized
4
🛠

Basal Ganglia Memory

8

This skill is designed to help AI agents learn and form habits.

safe Productivity & Tasks
4
🛠

Self Learning Skill

by davidme6

6

This skill is designed to help an AI agent learn from its mistakes and improve its problem-solving abilities by analyzing issues, identifying patterns, and generalizing solutions.

review Uncategorized
4
🛠

Footballbin Predictions

by billychl1

7

Provides AI-powered predictions for football matches, including scores and goal information, for the Premier League and Champions League.

safe AI & LLMs
4
🛠

Software Copyright Cn

by binbin

6

This skill helps users generate application materials for Chinese computer software copyright registration, including source code and documentation PDFs.

review Git & GitHub
4
🛠

Batch Processing Patterns

by bingfoon

6

This skill provides guidance and patterns for handling batch processing tasks, such as file manipulation, API calls, and background jobs, including features like concurrency control, error handling, and progress reporting.

review AI & LLMs
4
🛠

Cherry Mcp

by bitbrujo

6

This skill acts as a bridge to keep MCP servers running and accessible via a local HTTP REST API, allowing OpenClaw agents to use MCP tools.

review CLI Utilities
4
🛠

Macclaw Copilot Cli

by biuyx

5

This skill helps you use GitHub Copilot CLI to analyze your code by asking it questions.

review Git & GitHub
4
🛠

Exe Dev

by bjesuiter

6

This skill helps you manage virtual machines hosted on exe.dev, allowing you to create, configure, and share them for hosting or development.

review Uncategorized
4
🛠

Call Claude Sonnet 4 Agent

8

This skill acts as an AI agent designed to perform tasks related to calling the Claude Sonnet 4 model.

safe Productivity & Tasks
4
🛠

Cpskilltest123456

by blockcloud

8

This skill helps you publish long-form articles on the Xiaohongshu platform by automating browser actions.

safe Uncategorized
4

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.