Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Skill Factory
This skill helps you create, evaluate, improve, benchmark, and publish OpenClaw skills.
Snipgrapher
This skill helps you create polished images of code snippets.
Tootoo Skill
This skill helps synchronize your 'TooToo codex' and monitor agent alignment with your values.
Strudel Music
This skill allows you to create, generate, and play music using live-coding techniques.
Sunday
This skill helps manage your email address and a secure vault for your encrypted credentials.
Twitter Api
This skill provides tools for automating tasks on Twitter/X, such as managing your timeline, notifications, and posting.
Video Captions Reelwords
This skill generates captions for short-form videos by using the ReelWords Caption API.
Video Upload Aioz Stream
This skill helps you quickly upload videos to the AIOZ Stream API.
Voiceai Voiceover Creator
This skill helps you turn scripts into voiceovers, including features like segments, chapters, captions, and video muxing.
Youtube Hook
This skill helps you create engaging content for YouTube videos, including scripts, titles, descriptions, and thumbnail ideas.
Youtube Knowledge Extractor
Analyzes YouTube videos by processing both their audio transcripts and visual frames.
Ytwatchervideo
This tool helps you get the text transcript from YouTube videos.
Agentns
This skill helps AI agents register and manage internet domain names through ICANN.
Agent Rate Limiter
This skill helps manage API rate limits by automatically adjusting request frequency.
Artifacts Builder
This skill provides a set of tools for building complex, multi-part projects.
Bitrix24 Apiskill
This skill helps integrate AI agents with the Bitrix24 platform using its REST API and OAuth 2.0.
Comfyui Runner
This skill helps you start, stop, and check the status of a ComfyUI instance.
Copilotkit Runtime Patterns
This skill provides server-side runtime patterns for CopilotKit.
Enterprise Legal Guardrails Public
This skill helps ensure outbound actions comply with legal and privacy regulations.
Guardian Core
This skill acts as a local security scanner with a dashboard and pre-defined threat signatures.
Hf Spaces
This skill helps you generate images, videos, audio, and other content using HuggingFace Spaces and Inference Providers.
Kagi Enrich
This skill searches Kagi's unique non-commercial web and non-mainstream news indexes for independent, ad-free content.
Loopwind
This skill helps you create images and videos from React and Tailwind CSS templates using a command-line tool.
Mercury Payments
This skill helps you pay invoices using the Mercury Bank API.
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.