improve-codebase-architecture

Analyze module interfaces and seams to surface actionable deepening opportunities.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/yarma-tech/agent-admin-qonto --skill improve-codebase-architecture-yarma-tech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: improve-codebase-architecture
Source: https://github.com/yarma-tech/agent-admin-qonto/tree/main/.agents/skills/improve-codebase-architecture
Command: npx skills add https://github.com/yarma-tech/agent-admin-qonto --skill improve-codebase-architecture-yarma-tech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Surface architectural friction by surfacing shallow modules and seams, then proposing concrete deepening opportunities to improve testability and AI-navigability.

Core Features & Use Cases

  • Surface friction points by identifying shallow modules, seams, and potential adapters.
  • Propose actionable deepening opportunities aligned with domain language and ADRs.
  • Guide teams through the grilling loop to select and validate refactor candidates that improve locality and leverage.

Quick Start

Analyze the repository to surface a concrete deepening opportunity for the codebase.

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 points in my codebase?▼

Architectural friction points are identified by analyzing shallow modules, seams, and potential adapters. This process surfaces concrete deepening opportunities to improve testability and AI-navigability.

What is a deepening opportunity in software architecture?▼

A deepening opportunity is an actionable architectural improvement targeting shallow modules and seams. It improves testability, locality, and AI-navigability while adhering to existing ADRs and domain language.

How do I refactor a codebase to improve modularity and testability?▼

Refactor to improve modularity and testability by analyzing module interfaces and applying the project domain language from CONTEXT.md. This surfaces implementation-agnostic recommendations that fit existing ADRs.

Can I use ADRs to guide codebase refactoring decisions?▼

Yes, ADRs guide codebase refactoring by constraining exploration to high-impact areas. Recommendations are designed to preserve safety and consistency with project taxonomy and existing ADRs.

What is the best way to improve AI-navigability in a codebase?▼

The best way to improve AI-navigability is by surfacing and resolving deepening opportunities in shallow modules. This process applies project domain language and targets high-impact architectural areas.

When should I not use architectural refactoring on my codebase?▼

Avoid architectural refactoring when it compromises safety or violates existing ADRs. Recommendations must preserve consistency with project taxonomy and remain implementation-agnostic to avoid unnecessary friction.