Code Research Crafter

English | 简体中文

A complete workflow for researching codebases, designing enhancement proposals, and publishing RFCs to GitHub.

🎯 What is Code Research Crafter?

Code Research Crafter is a comprehensive skill that provides a structured 6-phase workflow for deep codebase research and professional proposal crafting. It bridges the gap between code analysis and community engagement through evidence-based technical writing.

✨ Key Features

• 🔍 Systematic Code Analysis - Explore and understand complex codebases with structured methodologies
• 📚 Academic Research Integration - Find and cite relevant papers, algorithms, and prior art
• 👥 Community Intelligence - Analyze GitHub issues, discussions, and maintainer feedback
• 🏗️ Architecture Design - Create layered solutions with data models and phased implementation plans
• 📝 Professional Documentation - Generate structured technical documents in multiple languages
• 🚀 RFC Publication - Write and submit professional RFCs to open-source communities

🔄 The 6-Phase Workflow

Phase 1: Problem Discovery & Code Analysis

Identify target areas, perform deep code analysis, and document findings with quantified metrics.

Phase 2: Academic & Community Research

Search for academic papers, extract key insights, and analyze GitHub community discussions.

Phase 3: Solution Design

Define design principles, architect layered solutions, design data models, and plan implementation phases.

Phase 4: Documentation Generation

Generate comprehensive technical documents with proper structure and citations.

Phase 5: English RFC Writing

Craft professional RFC markdown documents following open-source community standards.

Phase 6: GitHub Publication

Submit RFCs to GitHub with proper formatting and community engagement.

📖 When to Use This Skill

Use Code Research Crafter when you need to:

• ✅ Analyze an open-source codebase and propose enhancements
• ✅ Research technical problems with academic rigor
• ✅ Design system architectures with evidence-based decisions
• ✅ Create professional RFCs for open-source communities
• ✅ Document complex technical proposals with proper citations

🏗️ Example Outputs

This skill has been successfully used to create:

• Memory Consolidation RFC - Combining Zettelkasten + PPR + Sleep Consolidation approaches
• Multi-Agent Collaboration RFC - With Capability Profiling and Shared Blackboard architecture
• Temporal Decay Bug Fixes - Expanding date pattern recognition
• i18n Translation Improvements - For configuration interfaces

🎨 Design Principles

1. Evidence-Based Analysis - Quote specific code locations and quantify problems
2. Academic Rigor - Reference recent papers (2024-2025) with proper citations
3. Human-Centered Design - Use organization analogies and design for gradual adoption
4. Cost Awareness - Track token/performance implications and design for efficiency
5. Community Engagement - Reference existing issues and invite collaboration

🛠️ Tools & Resources

This skill leverages various tools for comprehensive research:

• Code Analysis: glob, grep, read
• Academic Research: WebSearch, WebFetch
• Documentation: python-docx for professional document generation
• Publication: browser_use_desktop for GitHub submission
• Version Control: desktop_terminal_execute for Git operations

📦 Installation

This is a skill designed for use with AI assistants. To use it:

1. Clone this repository
2. Place the skill files in your skills directory
3. Reference the skill in your AI assistant configuration

git clone https://github.com/zz0116/code-research-crafter.git

🚀 Quick Start

1. Identify your target - Choose a codebase or technical problem to research
2. Follow the workflow - Work through the 6 phases systematically
3. Document as you go - Capture findings, insights, and decisions
4. Engage the community - Share your RFC and gather feedback

📋 Common Patterns

Layered Architecture

Layer 1: Foundation (data collection)
Layer 2: Enhancement (builds on L1)
Layer 3: Intelligence (AI/ML on data)
Layer 4: Governance (control/monitoring)

Dual-Track Data

• User-defined (static): config, prompts
• System-learned (dynamic): metrics, patterns

Visibility Tiers

• private: owner only
• team: collaborators
• global: all users

📊 Success Metrics

A successful Code Research Crafter output should:

• ✅ Receive community engagement (comments, reactions)
• ✅ Quantify problems with code evidence
• ✅ Reference academic research
• ✅ Provide phased, actionable implementation plans
• ✅ Be clear for all audiences

🤝 Contributing

Contributions are welcome! Please feel free to submit issues, fork the repository, and create pull requests.

📄 License

This project is licensed under the MIT License - see the LICENSE.txt file for details.

🙏 Acknowledgments

• Thanks to all open-source communities that inspired this workflow
• Academic researchers whose papers inform our solutions
• Contributors who help improve this skill

---

Craft better proposals. Build better software. 🚀