Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Vscode Tunnel
This skill helps you set up VS Code for remote access within Docker containers.
Wolt Cli
This skill allows you to interact with a local Wolt command-line interface to browse restaurants, view menus, and manage your shopping cart.
Core Prompt Patcher
This skill automatically synchronizes your workspace persona from a SOUL.md file into the OpenClaw system.
Exponential
This skill helps you manage tasks, projects, and workspaces using a command-line tool called `exponential`.
Find Emails
This skill aims to find and extract email addresses from websites by using a tool called crawl4ai.
Hostinger
This skill helps you manage your Hostinger account, including your VPS, backups, and firewall, through an API.
Playwright Scraper Skill
This skill uses Playwright to scrape websites and includes features to bypass anti-bot measures.
Preqstation
This skill helps you with coding tasks by using other AI coding tools like Claude Code, Codex CLI, or Gemini CLI.
Scrapling
This skill is designed to scrape websites, including techniques to bypass bot detection and crawl through sites.
Solo Deploy
This skill helps deploy your project to a hosting platform by reading your project's configuration and detecting necessary command-line tools.
Twinify
This skill aims to create AI representations of people based on their WhatsApp chat history.
Video Download
This skill helps you download videos from many websites and create subtitles for them using an AI tool.
Ambit Cli
This skill helps you manage private networks and deploy applications using a tool called the 'ambit CLI'.
Aws Agentcore Langgraph
This skill helps deploy LangGraph agents on AWS.
Bind Protocol Mcp
This skill is designed to help manage credentials, create policies, and generate proofs using a protocol called Bind.
Mh Blogwatcher
This skill monitors blogs and RSS/Atom feeds for updates using a command-line tool.
Mobilerun
This skill allows you to control real Android phones through a specific API.
Opnsense Admin
This skill helps manage your OPNsense firewall, DNS, and network settings.
Summarizerx64
This skill helps you summarize the content of URLs or files using a command-line tool.
Vps Health Auditor
This skill performs system health checks and analyzes the results using an AI model.
Minara
This skill helps you manage cryptocurrency trading, including swaps, futures, transfers, payments, deposits, and withdrawals.
Activity Analyzer
Analyzes your computer activity using the ActivityWatch tool.
Craft Cli
This skill allows you to interact with Craft documents using a command-line tool.
Kraken
This skill helps you interact with your Kraken account using a command-line tool.
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.