Agent Skills Hub

novelty-check

Verify research idea novelty against recent literature. Use when user says '查新', 'novelty check', or needs to confirm if a method is original.

evidence-first-debugging

Enforces a strict evidence-based debugging workflow using structured observation, hypothesis testing, and causality validation to eliminate speculation in technical investigations.

rag-implementation

Build production-grade RAG systems using vector databases, semantic search, and LangGraph to ground LLMs in external knowledge.

creative-thinking-for-research

Applies cognitive science frameworks for creative thinking to generate genuinely novel research directions in computer science and AI.

mcp-development

Guidance for Model Context Protocol (MCP) server development, including tool design, resource handling, and AI/ML integration patterns.

open-source-maintainer

End-to-end GitHub repository maintenance agent. Automates triage, PR review, issue analysis, and maintenance reporting to ensure long-term repository health, stability, and growth.

prd

Generate professional Product Requirements Documents (PRD) and structure features for autonomous development cycles.

wenxian

Automated academic literature retrieval, structured summarization, and multi-channel scheduling workflow for research topics.

prp-ralph-loop

Autonomous iteration loop for AI software development. Executes tasks, validates code, and manages state until completion. Ideal for implementing complex PRP plans.

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.

developer-growth-analysis

Analyzes Claude Code chat history to identify coding patterns and skill gaps, curates personalized learning resources from HackerNews, and sends progress reports to Slack.

tapestry

Unified content extraction and action planning engine. Automatically processes URLs (YouTube, articles, PDFs) into actionable plans.