Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Mintyouragent
This skill is designed to help users interact with the Solana blockchain, create tokens, and play poker, while also linking their identity to a specific website.
Nano Banana Cog
This skill appears to be a placeholder or a very basic integration with no clearly defined function.
Nano Banana Pdf Skill
This skill allows you to edit PDF files using natural language commands with a command-line tool.
Native Run
This skill allows you to run native commands on your computer.
Onebot Adapter
This skill helps integrate OpenClaw with the OneBot protocol to connect with QQ bots.
Ozel Yetenek
This skill is designed to review other 'openclaw' skills.
Parakeet Local Asr
Installs and runs a local speech-to-text system that is compatible with OpenAI's transcription API.
Paylobster
This skill is designed to manage agent payments on the Base blockchain.
Permissions Broker
This skill acts as a default way to access external data and perform actions with third-party services when local login information isn't available.
Personality Dynamics
This skill is designed to dynamically evolve the personality of OpenClaw agents.
Personality Switcher
This skill allows you to create and switch between different AI assistant personalities.
Preqstation Preqstation
This skill aims to let you use AI coding tools like Claude Code, Codex CLI, or Gemini CLI through natural language commands.
Pumpfun Launch
This skill aims to help you launch tokens on the pump.fun platform.
Quantumos
This skill aims to install and manage a system called QuantumOS, described as an AI command center for OpenClaw.
Quick Reminders
This skill is designed to set short-term reminders using a background process and a messaging tool.
Ralphie
This skill aims to install and operate a tool called Clawboard with OpenClaw.
Rhandus File Management
This skill helps manage Google Drive files using a command-line tool called 'gog CLI'.
Rmn Soul
This skill aims to enhance an AI agent's memory and identity using advanced concepts.
Safe Update
This skill is intended to update a tool called OpenClaw from its source code.
Samma Suit
This skill aims to enhance the security features of an agent by adding controls like budget management, permissions, and logging.
Sec Watcher
This skill monitors SEC EDGAR filings for AI and technology companies in real time.
Skill Hub
This skill is intended to help users discover, vet, and install other OpenClaw skills.
Security Operator
This skill is intended to provide runtime security guardrails for OpenClaw agents.
Simplify And Harden
This skill helps coding agents review and improve their own code by applying simplification, hardening, and documentation steps.
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.