Agent Skills Hub

monitor

Automated PR CI monitoring and failure resolution agent.

skill-architect

Expert consultant for designing and building high-quality, consistent AI agent skills. Guides you through discovery, architecture, and creation phases to ensure reliable, composable, and efficient skill delivery.

web-shader-extractor

Extract, deobfuscate, and port WebGL/Canvas/Shader visual effects from websites into standalone, native JavaScript projects.

文档分析器

Deep document structure analysis and intelligent content extraction for knowledge bases.

wrap

Automated session cleanup and documentation tool. Proactively updates CLAUDE.md, detects automation patterns, extracts insights, and organizes pending tasks.

trulens-evaluation-workflow

A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.

analytics-interpretation

Analyze GA4 and GSC performance data with automated benchmarks, status indicators, and actionable content optimization insights.

feature-dev

Guided, systematic feature development agent that orchestrates codebase exploration, architectural design, implementation, and automated testing.

coach

A persistent, adaptive coaching assistant that analyzes your Claude Code session history to recommend personalized skills and improve your AI collaboration patterns.

react-expert

Research React APIs, patterns, and concepts using authoritative source code, tests, and repository history.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.