repo-research

Analyze repository structure and metadata to generate project-context.md.

Updated Apr 4, 2026

Search Tags:#architecture #documentation #onboarding #codebase #analysis #repository #project-context

Ready to run

npx skills add https://github.com/Mtettey29/restaurant-concierge-sdd --skill repo-research-mtettey29

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: repo-research
Source: https://github.com/Mtettey29/restaurant-concierge-sdd/tree/main/.agents/skills/repo-research
Command: npx skills add https://github.com/Mtettey29/restaurant-concierge-sdd --skill repo-research-mtettey29

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes a repository's structure and metadata to generate a structured, up-to-date project-context.md that guides onboarding, architecture decisions, and governance.

Core Features & Use Cases

Phase-driven surface scan and phased knowledge extraction to avoid bulk reads.
Outputs to .agents/rules/project-context.md containing project identity, technology stack, configuration hints, and architecture notes.
Supports onboarding, architecture reviews, and audits by providing a living, consultable reference document.

Quick Start

Run the phased repository analysis to generate or update the project-context.md.

Frequently Asked Questions about repo-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate project context documentation for onboarding from an existing codebase?▼

To analyze repository architecture, run a phased workflow that reads structure first, then configuration, entry points, data models, and performs targeted deeper dives. It outputs architecture notes to .agents/rules/project-context.md for review.

What is the best way to document codebase architecture without reading every file?▼

Use a phase-driven surface scan to extract repository knowledge incrementally. It reads only structure in Phase 1, then config in Phase 2, entry points in Phase 3, and targeted deeper dives in Phase 4 to avoid bulk reads.

Can I use automated codebase analysis for repositories of varying languages and sizes?▼

Yes, this repository analysis applies to codebases of varying languages and sizes. It extracts project identity, technology stack, and configuration hints to generate a living reference document for audits and reviews.

Where does the generated repository context and documentation get saved?▼

The generated repository context and documentation gets saved directly to .agents/rules/project-context.md. This file contains project identity, technology stack, configuration hints, and architecture notes for continuous consultation.

Do I need any dependencies or components installed to run codebase analysis?▼

No dependencies or components are required to run codebase analysis. The phased workflow operates independently to scan repository structure and metadata, outputting updates to the project-context.md file.