improve-codebase-architecture

Scan domain glossaries, ADRs, and CONTEXT.md to surface architectural deepening opportunities.

5|Updated Oct 18, 2025
One-click install
npx skills add https://github.com/rexshihaoren/rexyDigest --skill improve-codebase-architecture-rexshihaoren
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve-codebase-architecture
Source: https://github.com/rexshihaoren/rexyDigest/tree/main/docs/ai/skills/improve-codebase-architecture
Command: npx skills add https://github.com/rexshihaoren/rexyDigest --skill improve-codebase-architecture-rexshihaoren

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps software teams surface architectural frictions and identify deepening opportunities to improve testability and AI-navigability of large codebases.

Core Features & Use Cases

  • Discovery: Scan domain glossaries, ADRs, and CONTEXT.md to surface architectural friction points.
  • Candidate Presentation: Generate a prioritized list of deepening opportunities with rationale and impact.
  • Grilling Loop: Engage in a back-and-forth grilling process to refine candidates with constraints and trade-offs.
  • Use Case: When refactoring a monolith, use this Skill to propose seam placements and potential adapters to enable safer incremental changes.

Quick Start

Run the agent-guided analysis to surface deepening opportunities in the current 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 find deepening opportunities to improve codebase architecture?

To find deepening opportunities, scan your domain glossary, CONTEXT.md, and ADR records to surface friction points. This generates a prioritized list of candidates to introduce seams and adapters for better testability.

What are seams and adapters when refactoring a monolith?

Seams and adapters are structural boundaries introduced incrementally to isolate dependencies during a monolith refactor. They reduce risk by enabling safer changes and improving codebase testability without a full rewrite.

How do I plan an incremental refactor using ADR records?

Plan an incremental refactor by scanning ADR records and CONTEXT.md to formalize deepening candidates into a structured plan. A grilling loop then refines these proposals with constraints and trade-offs.

Can I use this for architecture reviews on large codebases?

Yes, this is explicitly applicable during architecture reviews of large codebases. It reads existing domain glossaries to uncover deepening opportunities that improve AI-navigability and manage risk.

What is the best way to prioritize architectural friction points?

Prioritize architectural friction points through an agent-guided grilling loop. This back-and-forth process evaluates deepening candidates against project constraints to produce a structured, high-impact refactor plan.