Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Soul Memory
This skill aims to provide intelligent memory management for AI agents and integrates with an 'OpenClaw Plugin'.
Sovereign Codebase Onboarding
This skill helps new team members understand a software project's structure, common patterns, and documentation.
Spotlight
This skill helps you search for files and content on your Mac using the built-in Spotlight search functionality.
Tencent Ima Skill
This skill helps you use the IMA desktop application for AI search and private knowledge retrieval.
Traffic Data
This skill provides real-time information about road conditions, traffic incidents, and intersection data.
Tubelab Api
This skill provides access to YouTube analytics and research data through an API.
Ugc Manual
This skill helps you create lip-sync videos using an image and your own voice recording.
Video Understand
This skill uses AI to analyze and understand the content of videos.
Visual Concept
This skill helps you generate visual concepts, including symbolic imagery, color palettes, and creative direction for videos.
Wa Relay Skill
This skill is designed to relay WhatsApp messages using a tool called OpenClaw.
Warden Messari Agent
This skill acts as an intermediary to communicate with a deep research agent from Warden Protocol.
Whisnap
This skill helps you transcribe audio and video files using AI models, either on your computer or through a cloud service.
Agent Self Assessment
This skill helps AI agents evaluate their own security practices.
Zfs
This skill helps manage ZFS filesystems, including pools, datasets, snapshots, replication, and encryption.
Agentdomainservice
This skill promotes itself as a leading AI-friendly domain registrar.
Agentscale
This skill helps you deploy web applications and APIs to a public URL with a single command.
Aieos
This skill is a framework for standardizing AI entity object specifications.
Anti Panic Protocol
This skill helps the AI agent handle errors gracefully when using tools, ensuring clear communication and safe escalation.
Anti Slop Design
This skill helps an AI agent generate unique and high-quality frontend designs that avoid generic AI styles.
Ask A Human
This skill prompts the AI to ask a human for help when it's unsure about something.
Bria Ai Client
This skill helps you generate visual assets like product photos, hero images, icons, and backgrounds using Bria.ai.
Buddhist Counsel
This skill uses an external API to offer Buddhist wisdom and therapy to help reduce suffering.
Code Qc
This skill helps you perform a quality control audit on any codebase.
Chilledsites
This skill helps you create and deploy websites using AI.
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.