improve-codebase-architecture

Identify shallow modules and generate an HTML report with refactoring recommendations.

Updated May 16, 2026
One-click install
npx skills add https://github.com/ckyeon/claude-code-settings --skill improve-codebase-architecture-ckyeon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve-codebase-architecture
Source: https://github.com/ckyeon/claude-code-settings/tree/main/user/shared/skills/improve-codebase-architecture
Command: npx skills add https://github.com/ckyeon/claude-code-settings --skill improve-codebase-architecture-ckyeon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill identifies shallow modules in a codebase and suggests refactoring opportunities to improve architecture, making the codebase more testable and AI-navigable.

Core Features & Use Cases

  • Deepening Opportunities: Surface architectural friction and propose refactoring opportunities to turn shallow modules into deep ones.
  • Domain Language: Uses the domain language in CONTEXT.md and architectural decisions in docs/adr/ to inform suggestions.
  • HTML Report: Generates a self-contained HTML report with visualizations and recommendations for refactoring.

Quick Start

Run the improve-codebase-architecture skill to analyze your codebase and receive architectural suggestions.

Frequently Asked Questions about improve-codebase-architecture

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

FAQPage Schema
How do I identify shallow modules in my codebase for refactoring?

To identify shallow modules, analyze your codebase architecture to surface friction and propose deepening opportunities. This refactoring turns shallow modules into deep ones, making your codebase more testable and AI-navigable.

What is a deep module in codebase architecture?

A deep module in codebase architecture is a component with a rich interface but minimal implementation details exposed. Deepening shallow modules improves testability and makes the codebase AI-navigable by hiding internal complexity behind a robust interface.

How do I use domain language and architectural decisions to inform refactoring suggestions?

Refactoring suggestions are informed by reading domain language from a CONTEXT.md file and architectural decisions from docs/adr/. This ensures that codebase architecture improvements align with your project's established terminology and design rationale.

Can I generate a visual report of codebase refactoring opportunities?

Yes, you can generate a visual report of codebase architecture refactoring opportunities. The analysis produces a self-contained HTML report that includes visualizations and actionable recommendations to guide your deepening efforts.

Does this codebase architecture analysis require any specific dependencies?

No, this codebase architecture analysis requires no external dependencies to run. It operates directly on your project files, relying on existing CONTEXT.md and docs/adr/ directories to inform its architectural suggestions.

When should I not use automated refactoring suggestions for my codebase?

You should avoid relying solely on automated refactoring suggestions when your codebase lacks a CONTEXT.md or docs/adr/ directory. Without domain language and architectural decision records, the generated deepening opportunities may lack proper context.