Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Geepers Llm
This skill allows you to interact with the dr.eamer.dev LLM API for various tasks including chat, image analysis, and generation.
Jable
This skill helps you find and sort the latest videos from Jable based on their popularity.
Kiro Search Aggregator
This skill is designed to perform multi-source searches within the OpenClaw environment.
Ms Foundry Image Gen
This skill helps generate images using a Foundry deployment.
Multi Factor Strategy
This skill helps users create and configure multi-factor strategies for selecting stocks.
Obekt Security
This skill performs basic security analysis on code, files, and other agent skills.
Publer
This skill allows you to post content to social media platforms using the Publer API.
Ui Controller
This skill allows for the control of your computer's user interface.
Ralstp Consultant
This skill is designed to help analyze problems using a strategic planning methodology called RALSTP.
Robonet Workbench
This skill helps you build, test, and deploy trading strategies using the Robonet platform.
Search Memory
This skill helps you search and index your local memory for Openclaw.
Seithar Intel
This skill acts as a personal cyber threat intelligence and cognitive security analyst.
Shrimp Plaza
Connects your AI agent to a Chinese social hub where AI agents interact as 'shrimps'.
Skillsentry
This skill helps audit security and detect prompt injection vulnerabilities.
Tiktok Product Promotion
This skill instructs an AI agent to find and engage TikTok influencers for product promotion activities.
Tokenqrusher
This skill aims to optimize tokens for OpenClaw, potentially reducing costs.
Youtube Ai Videos
This skill finds and filters the latest AI-related videos from specific YouTube channels.
Youtube Factory
This skill aims to create entire YouTube videos, including scripts, voiceovers, footage, captions, and thumbnails, from a single user prompt.
Youtube Summary
This skill helps you summarize YouTube videos into structured Markdown format, including chapter notes and timestamp links.
Arc Free Worker Dispatch
This skill helps you use free AI models through OpenRouter to reduce costs.
Ask Council
This skill allows you to ask a question to an AI council and receive a synthesized answer directly within your chat interface.
Civitai Api Art
This skill helps you create AI-generated artwork by using the CivitAI JavaScript SDK.
Context Slimmer
This skill helps manage and potentially reduce the size of internal agent configuration files.
Ddg 1 0 0
This skill helps you perform privacy-focused web searches directly from your command line using the `ddgr` 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.