Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Lol Drift Blooms
This skill describes a conceptual framework for playful interactions involving humor and looseness.
Skill Security Reviewer
This skill is a placeholder or metadata entry and does not perform any user-facing function.
Sovereign Commit Craft
This skill acts as an expert assistant for crafting Git commit messages.
Upstream Recon
This skill helps you research open-source projects by looking at their pull requests, issues, and comments.
Add Top Openrouter Models
This skill helps synchronize OpenRouter models used by OpenClaw into your current installation's configuration.
Agent Estimation
This skill helps an AI agent estimate the effort required for tasks using its own internal operational units.
Agent Puzzles
This skill offers AI-powered puzzle challenges with timed solving and leaderboards.
Agentgate Security
This skill is intended to act as an enterprise security firewall for OpenClaw.
Agentok Skill
This skill is designed to help AI agents interact with TikTok.
Ai Notes Ofvideo
This skill helps you generate notes from videos in various formats like documents, outlines, or graphic text.
Aimine
This skill aims to perform 'Proof of AI Work' mining on the BNB Chain.
Alpha Finder
This skill provides market intelligence for prediction markets like Polymarket and Kalshi.
Audio Upload Aioz Stream
This skill helps you quickly upload audio files to the AIOZ Stream API.
Bitnote
This skill aims to provide decentralized and encrypted storage for an agent's secrets, identity, and memories.
Brw Voice Extractor
This skill helps you analyze and document the unique writing style found in text samples.
Capability Awareness
This skill helps AI agents understand and utilize custom capabilities.
Chia Splitxch
This skill helps you generate cryptocurrency addresses for splitting royalty payments based on your descriptions.
Chinese Llm Router
This skill helps you connect to and chat with different Chinese AI models without complex setup.
Claude Code Legacy
This skill helps manage and visualize development tasks within tmux sessions.
Claude Optimised
This skill provides guidance on how to write and optimize CLAUDE.md files.
Config Field
This skill checks your OpenClaw configuration files to make sure they follow the correct format.
Consilium
This skill acts as a personal board of AI advisors, utilizing different AI models for advice.
Content Ideas Free
This skill is a free tool for brainstorming content ideas.
Creative Ops Copilot
This skill helps you organize messy client briefs into a structured plan for motion design and VFX projects.
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.