What problem does it solve? Developers often inherit code, review AI-generated implementations, or face unfamiliar systems without a clear mental model of how they work or where to debug failures. This Skill builds genuine understanding through a guided, step-by-step teaching session rather than a one-shot explanation dump. ## Core Features & Use Cases - Interactive Walkthroughs: Teaches code one small step at a time, asking focused application questions and adapting based on the user's answers through a clarification loop. - Scoped Subjects: Supports keyword scopes like changes, staged, head, branch, file, and system to target exactly the code or Git diff the user wants explained. - Architecture Coherence Checks: Evaluates responsibility placement, dependency direction, duplication, and file organization, surfacing concrete concerns with evidence. - Use Case: After an AI agent implements a feature, ask for a walkthrough of the branch changes to verify you understand the control flow, ownership boundaries, and where to start debugging before merging. ## Quick Start Ask the assistant to explain how the authentication system works using the understand-code skill, starting with its main execution path.
