improve_codebase_architecture

Analyze codebases to surface architectural friction and draft module-deepening RFCs.

20|6|Updated Jan 16, 2026
One-click install
npx skills add https://github.com/adrielp/ai-engineering-harness --skill improve-codebase-architecture-adrielp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve_codebase_architecture
Source: https://github.com/adrielp/ai-engineering-harness/tree/main/gemini/skills/improve_codebase_architecture
Command: npx skills add https://github.com/adrielp/ai-engineering-harness --skill improve-codebase-architecture-adrielp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Explore a codebase like an AI would, surface architectural friction, discover opportunities for improving testability, and propose module-deepening refactors as RFC issues.

Core Features & Use Cases

  • Surface architectural friction by analyzing module boundaries and dependencies.
  • Propose deepening opportunities and RFC-ready design candidates across the codebase.
  • Generate RFC-worthy interface designs and an issue draft to guide refactors.

Quick Start

Analyze the repository to surface architectural friction and propose module-deepening RFCs.

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 architectural friction in my codebase?

Architectural friction is identified by analyzing module boundaries and dependencies to surface areas where shallow modules hinder testability, then proposing deep-module refactors as RFC issues.

What is a deep-module refactor and when do I need one?

A deep-module refactor simplifies a complex interface while hiding implementation details. You need one when architectural friction causes shallow modules with poor abstraction and reduced testability.

How do I create an RFC-ready description for codebase refactoring?

Create an RFC-ready description by analyzing the codebase to outline a plan for deepening shallow modules, generating structured interface designs and an issues draft to guide the refactor.

Can I analyze a codebase of any size or language for module-deepening opportunities?

Yes, you can apply architectural analysis to codebases of varying sizes and languages to discover opportunities for improving testability and propose deep-module refactoring candidates.

What is the best way to improve testability through architecture analysis?

The best way to improve testability is to surface architectural friction across module boundaries and frame RFCs that propose deepening shallow modules to improve structural design.