What problem does it solve? Codebases accumulate shallow modules whose interfaces are nearly as complex as their implementations, making them hard to test and navigate. This Skill surfaces that architectural friction and proposes concrete deepening refactors, so you can decide what to fix based on evidence rather than gut feel. ## Core Features & Use Cases - Hot-spot-driven scanning: Uses git history to find frequently changed areas, then delegates exploration to a context-isolated scout agent that applies the deletion test to detect shallow modules, leaky seams, and poor locality. - Visual HTML report: Renders each candidate refactor as a self-contained HTML file (Tailwind and Mermaid via CDN) with before/after diagrams, problem/solution summaries, and a recommendation strength badge, written to the OS temp directory. - Guided decision loop: After you pick a candidate, it walks constraints, dependencies, and interface shape through a grilling workflow, updating CONTEXT.md and offering ADRs when decisions carry lasting weight. - Use Case: Run it on a service where order handling logic is scattered across six thin wrappers; get a report showing how to collapse them into one deep module with a single testable interface. ## Quick Start Ask the agent to scan this repository for architecture improvements and show me the deepening candidates as an HTML report.
