improve-codebase-architecture

Identify architectural friction and surface module deepening candidates with coupling signals.

99|6|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/vvedantb/eva --skill improve-codebase-architecture-vvedantb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve-codebase-architecture
Source: https://github.com/vvedantb/eva/tree/main/.agents/skills/improve-codebase-architecture
Command: npx skills add https://github.com/vvedantb/eva --skill improve-codebase-architecture-vvedantb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps engineering teams identify architectural friction in a codebase and surface opportunities to deepen shallow modules, enabling better testability and AI-navigable structures.

Core Features & Use Cases

  • Surface deepening opportunities across modules by analyzing coupling, boundaries, and shared responsibilities.
  • Propose candidate refactors and interface designs to improve modularity and testability.
  • Generate a GitHub RFC-style plan outlining recommended changes and acceptance criteria for stakeholder review.

Quick Start

Ask the agent to start the Explore workflow on your repository to surface deepening opportunities.

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 and shallow modules in my codebase?

To identify architectural friction, analyze module coupling, shared responsibilities, and boundary clarity. This surfaces shallow modules and returns a prioritized set of deepening candidates with coupling signals and dependency categories to improve testability and AI navigability.

What is the best way to plan a codebase refactor for better modularity and testability?

The best way to plan a codebase refactor is to generate a GitHub RFC-style plan. This provides recommended interface designs, acceptance criteria, and prioritized module deepening candidates for stakeholder review and measurable refactoring outcomes.

How do I make my codebase architecture more AI-friendly and navigable?

To make your codebase architecture more AI-friendly, deepen shallow modules to establish clearer boundaries. Running an Explore workflow analyzes coupling signals and proposes interface designs that improve code access and navigability for AI agents.

Can I use this approach for refactoring a complex and growing repository?

Yes, this approach is applicable for refactoring complex and growing repositories. It analyzes the codebase to surface measurable refactors, clearer module boundaries, and deepening opportunities tailored for teams managing scaling codebases.

How do I create a GitHub RFC for refactoring module boundaries?

You create a GitHub RFC for refactoring module boundaries by analyzing deepening candidates and coupling signals. The process returns a structured RFC-style plan outlining recommended changes, interface designs, and acceptance criteria for stakeholder review.