What problem does it solve? Codebases accumulate shallow modules whose interfaces are nearly as complex as their implementations, making them hard to test and hard for AI agents to navigate. This Skill surfaces that architectural friction and turns it into concrete, visualized refactoring candidates. ## Core Features & Use Cases - Architecture exploration: Uses an Explore subagent plus git history hot-spot analysis to find shallow modules, seam leakage, and poor locality, applying the deletion test to validate candidates. - Visual HTML report: Generates a self-contained HTML file in the OS temp directory with Tailwind and Mermaid via CDN, rendering before/after diagrams, recommendation-strength badges, and ADR conflict callouts for each candidate. - Grilling loop: After the user picks a candidate, runs a decision-tree grilling session that updates CONTEXT.md, offers ADRs for rejected candidates, and can invoke design-it-twice exploration of alternative interfaces. - Use Case: Point it at a subsystem where bugs keep recurring; it identifies that pricing logic leaks across seams, renders a before/after diagram of a deepened module, and walks you through the refactor decision. ## Quick Start Ask the agent to review the architecture of the order intake subsystem and show deepening opportunities as an HTML report.
