map-codebase

Map brownfield codebases by deep-reading files and generating skeleton LLDs, HLD, EARS, and arrow docs.

90|14|Updated Apr 11, 2026

Search Tags:#codebase #brownfield #map #ears #lld #hld #arrow-docs

Ready to run

npx skills add https://github.com/jszmajda/lid --skill map-codebase-jszmajda

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: map-codebase
Source: https://github.com/jszmajda/lid/tree/main/plugins/arrow-maintenance/skills/map-codebase
Command: npx skills add https://github.com/jszmajda/lid --skill map-codebase-jszmajda

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Bootstrap LID in an existing brownfield codebase by deeply reading the declared scope, proposing lens-based clustering options, generating skeleton LLDs, HLD, and EARS bottom-up, and creating arrow docs that prompt the user to flesh out the skeletons.

Core Features & Use Cases

Deep-read every file to ground design with concrete evidence
Propose 3–5 fundamentally different clustering lenses, not just variants
Generate skeleton LLDs, a bottom-up HLD, and EARS specs per segment, plus tree-mirrored arrow docs
Provide an overlay-ready docs/index scaffold and prompts for flesh out

Use this skill when mapping an existing project to LID, bootstrap arrows, or reverse-engineering the design in a live repository.

Quick Start

Invoke the /map-codebase workflow against your brownfield project to bootstrap arrows and skeletons.

Frequently Asked Questions about map-codebase

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

FAQPage Schema

How do I bootstrap LID and generate HLD in a brownfield codebase?▼

Map the codebase by deep-reading every file to generate skeleton LLDs, a bottom-up HLD, and EARS specs. This process also creates tree-mirrored arrow docs to help you flesh out the design skeletons.

What is the best way to reverse-engineer design and create arrow docs for an existing project?▼

Reverse-engineer design by deep-reading the declared scope and proposing lens-based clustering options. This generates an overlay-ready docs/index scaffold and arrow docs that prompt you to flesh out the recovered architecture.

How do I generate EARS specs and low-level designs from existing source files?▼

Generate EARS specs and skeleton LLDs by invoking the mapping workflow against your live repository. It deeply reads every file to ground the design with concrete evidence and outputs the specifications bottom-up per segment.

Can I scope the codebase mapping to a specific directory instead of the whole project?▼

Yes, codebase mapping supports scoped or whole-project operation. It requires repository access and uses explicit STOP gates at each phase, allowing you to control whether you map a specific directory or the entire project.

What are the limitations when proposing lens-based clustering for a large codebase?▼

The mapping proposes 3–5 fundamentally different clustering lenses, not just variants. It requires deep-reading every file in scope, which may be time-consuming for large repositories, and it only writes docs to specific directories.

Do I need repository access to map codebase and generate skeleton LLDs?▼

Yes, mapping a codebase requires access to repository contents to deep-read every file. It also needs the ability to write generated skeleton LLDs, HLD, EARS, and arrow docs under the docs/arrows, docs/intent, and docs/high-level-design paths.