Skill Library
AI capabilities from across the web (MCP / Agent Skills), 749 in total · some can become online tools
skillsbench
Evaluate the effectiveness and efficiency of AI agents using skills.
reverse-skills
Reverse engineering analysis skills, supporting over 40 AI programming tools.
shaping-skills
Project shaping and breadboarding design skills for Claude code.
skill-codex
Claude Code skill that delegates prompts to Codex for code analysis and editing.
Unity-Skills
AI automation skills designed specifically for Unity.
rust-skills
A Rust development assistant that provides deep-level solutions through a metacognitive framework.
app-store-preflight-skills
An AI agent skill for scanning iOS/macOS projects to detect App Store rejection patterns.
skill
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents.
gtm-engineer-skills
Tool-readyClaude Code skill to improve website AEO and GEO scores, featuring 16 foundational checks and 6 intelligent dimensions.
claude-code-skills
Claude Code Skills Marketplace offers 65 production-ready skills to enhance development workflows.
hack-skills
Empowers AI agents to become proficient实战 hackers.
skill-sample-nodejs-fact
A basic template for building an Alexa facts skill.
skills
Bankr Skills provides plug-and-play tools to help developers build more powerful agents.
Pika-Skills
Pika Skills is a set of open-source skill modules that extend the capabilities of AI coding agents.
code-review-skill
A comprehensive, modular code review skill tailored for Claude Code, supporting multiple languages and frameworks.
claude-skill-app-onboarding-questionnaire
Design and build high-conversion questionnaire-based onboarding flows for applications.
webgpu-claude-skill
Claude skill for developing graphics applications using Three.js and WebGPU.
dotnet-skills
Claude Code skills and sub-agents for .NET developers.
agents-cli
Transform any coding assistant into an expert for creating, evaluating, and deploying AI agents on Google Cloud.
raptor
RAPTOR is an autonomous security research framework based on Claude Code, designed for vulnerability scanning, validation, and remediation.
Cradle
The Cradle framework enables AI agents to complete complex computer tasks through powerful reasoning, self-improvement, and skill management.
tirith
Terminal security tool that intercepts malicious behaviors such as homograph URLs, pipe injection, and ANSI injection.
MathModelAgent
An Agent designed specifically for mathematical modeling, automatically completing modeling tasks and generating full papers.
agentic-stack
A portable .agent/ folder containing memory, skills, and protocols that preserves knowledge when switching between multiple coding agent tools.