What problem does it solve? Codebases accumulate shallow modules whose interfaces are nearly as complex as their implementations, scattering logic across tightly-coupled files and making testing and navigation difficult. This Skill surfaces that architectural friction and proposes concrete deepening refactors grounded in the project's own domain language and recorded decisions. ## Core Features & Use Cases - Deepening Opportunity Discovery: Explores the codebase with sub-agents to find shallow modules, pass-through abstractions, and tightly-coupled seams, applying the deletion test to validate each candidate. - Consistent Architecture Vocabulary: Enforces a shared glossary (module, interface, depth, seam, adapter, leverage, locality) so every suggestion uses the same precise terms, aligned with the project's CONTEXT.md domain language. - ADR-Aware Recommendations: Reads docs/adr/ before suggesting changes, flags candidates that contradict existing ADRs, and offers to record new ADRs when candidates are rejected for load-bearing reasons. - Parallel Interface Design: Spawns multiple sub-agents to design radically different interfaces for a chosen candidate, then compares them by depth, locality, and seam placement with an opinionated recommendation. - Use Case: A team inherits a service where business logic is smeared across dozens of small handlers. Use this Skill to get a numbered list of consolidation candidates, pick one, and walk through a grilling session that produces a deep module with a small interface and tests written at that interface. ## Quick Start Ask the assistant to review this codebase for architecture improvements and list deepening opportunities using the improve-codebase-architecture skill.
