Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Zhipu Cogview Image
This skill allows you to generate images using the Zhipu AI CogView model.
Drafts
This skill helps you manage notes in the Drafts app using command-line tools on your Mac.
Homebrew
This skill provides instructions for using the Homebrew package manager on macOS to install software.
Ics Import On Iphone
This skill helps you create calendar events by generating .ics files, especially when direct calendar access isn't available.
Birthday Reminder
This skill helps you manage your contacts' birthdays using simple text commands.
Clawdefender
This skill acts as a security scanner and input sanitizer for AI agents.
Clawdirect
This skill helps you interact with a directory of social web experiences called ClawDirect.
Chitin
This skill aims to help AI agents remember and maintain their personality over time.
Client Manager
This skill helps freelancers manage their clients, projects, invoices, payments, earnings, leads, and time.
Client Project Manager
This skill helps you manage freelance clients, projects, invoices, and communications.
Create Cli
This skill helps you design command-line interface arguments, flags, and subcommands.
Django Tool
This skill aims to simplify the process of setting up development environments.
Gmail Inbox Zero Triage
This skill helps manage your Gmail inbox using a command-line tool and Telegram buttons for interactive control.
Greek Banking Integration
This skill helps you process bank statements from major Greek banks.
Plusefin Analysis
This skill provides AI-powered analysis of stock market data, including options, sentiment, and predictions.
Presage
This skill connects to a prediction market terminal on the Solana blockchain.
Smart Cache
This skill helps manage data caching using strategies like Least Recently Used (LRU) and Least Frequently Used (LFU), along with time-to-live (TTL) settings.
Task Scheduler
This skill allows you to schedule commands or tasks to run at specific times.
Tvscreener
This skill helps you query stock market screener data from TradingView for various markets.
User Authentication System
This skill provides role-based access control for accounting firms in Greece.
Wind Site
Provides information about wind speed and direction at a specific location, useful for site and urban wind assessments.
Agent Defibrillator
This skill acts as a watchdog to automatically restart your AI agent if it crashes.
Swiftui Liquid Glass
This skill helps you implement, review, or improve features related to SwiftUI.
Symbolpicker
Provides expert guidance on using SymbolPicker, a tool for working with native SwiftUI SF Symbols.
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.