What problem does it solve? Codebases accumulate shallow modules whose interfaces are nearly as complex as their implementations, making code hard to test and hard for both humans and AI to navigate. This Skill surfaces that architectural friction and proposes concrete deepening refactors grounded in a shared design vocabulary. ## Core Features & Use Cases - Hot-spot-driven exploration: Scopes the scan using recent commit history (git log) or a user-named direction, then spawns a sub-agent to find shallow modules, seam leakage, and poor locality. - Visual HTML report: Renders each candidate as a before/after card in a self-contained HTML file (Tailwind + Mermaid via CDN) written to the OS temp directory, with recommendation-strength badges and ADR-conflict callouts. - Grilling loop: After the user picks a candidate, runs a decision-tree interview and keeps CONTEXT.md and ADRs current as decisions crystallize. - Use Case: A team notices their order intake flow is spread across six thin wrappers. Run this Skill to get a visual report of deepening candidates, pick one, and grill the design down to a single deep module with one testable interface. ## Quick Start Ask the agent to scan this repository for architecture deepening opportunities and present them as an HTML report.
