Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Moonbanking
This skill claims to provide access to data about every bank on Earth.
Neutron Agent Memory
This skill is designed to manage and access information stored by an agent using a specific API.
Oneshot
This skill is described as an SDK for AI agent commercial transactions.
Persistent Private Agent Memory
This skill aims to create a local service for an AI agent to remember and improve over time using cryptography.
Pubmed Edirect
This skill helps you search and retrieve scientific literature from PubMed using specialized command-line tools.
Pubmed2blog
This skill transforms PubMed research papers into blog articles optimized for search engines.
Rent A Human Agent
This skill allows you to delegate tasks to real people through the RentAHuman.ai service, enabling you to post jobs and manage conversations.
Skillzmarket
This skill allows users to find and use paid AI tools from a marketplace called Skillz Market, with payments handled automatically using USDC on the Base blockchain.
Tandoor Recipes
This skill helps you manage recipes, meal plans, and shopping lists within the Tandoor Recipe Manager application.
Whoo Cli
This skill uses a command-line tool called 'whoo' to fetch and interpret your WHOOP health data, including recovery, HRV, sleep, strain, and SpO2.
Xbio
This skill provides a command-line interface for interacting with X (formerly Twitter), allowing you to read, search, and post content.
Zvec Local Rag Service
This skill sets up a local service for semantic search using AI embeddings.
Ad Ready
This skill helps you create professional advertising images by using product URLs.
Auto Skill Hunter
This skill aims to find and install other tools or 'skills' from a platform called ClawHub based on your needs.
Botsee
This skill monitors your brand's visibility on AI platforms using the BotSee API.
Linkfuse
This skill helps you create shortened affiliate links from any web address.
Phone Caller
This skill aims to make AI-powered outbound phone calls using external voice and AI services.
Posthog Query
This skill allows you to run SQL queries against your PostHog product analytics data using the PostHog command-line interface.
Writing Group Leader
This skill configures the AI agent to act as a Writing Team Lead, managing specialized writers.
Agent Sentinel
This skill acts as a circuit breaker for the agent, intended to control its operations.
Anti Injection Skill
This skill claims to provide advanced defenses against prompt injection attacks, enhance memory integrity, and secure tools.
Anti Regression
This skill reminds the AI agent to stay focused on its task and avoid reverting to general chatbot behavior.
Askgina Polymarket
This skill helps you set up and trade on Polymarket using a provided Gina MCP token.
Gmail Secretary
This skill helps manage your Gmail inbox by classifying emails, applying labels, and drafting replies using an AI model and 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.