Improve Codebase Architecture: Let AI Conduct Architecture Review First Before Deciding Where to Modify

Matt Pocock’s `improve-codebase-architecture` is a user-invoked Agent Skill: it scans for shallow modules and leaky seams based on recent commit hotspots, filters candidates using deletion tests, drafts deepening opportunities into an off-repo HTML report (built with Tailwind + Mermaid), then conducts a grilling on the item you select. It does not modify business code, with the output being testable and navigable architectural decisions, before proceeding to to-spec, to-tickets and implementation stages. It is suitable for regular technical debt governance and structural health checks before major overhauls, rather than automated refactoring.