What problem does it solve?
Design discussions often leave assumptions unexamined and decisions half-made. This Skill runs a structured, relentless interview that surfaces every open design decision as a tree, asking all currently answerable questions in batched rounds until nothing is left silently assumed.
Core Features & Use Cases
- Design Tree Mapping: Models the design as a tree where each decision branches into dependent sub-decisions.
- Frontier-Based Rounds: Asks every question whose prerequisites are settled in a single numbered round, with recommended answers, then recomputes the frontier after each reply.
- Autonomous Fact-Finding: Dispatches sub-agents to look up facts from the filesystem or tools instead of asking the user for anything discoverable.
- Use Case: Before implementing a new feature, have the AI grill you on architecture, data models, error handling, and edge cases round by round until a shared, fully specified understanding is confirmed.
Quick Start
Ask the AI to grill you on your design for the new feature and map out the full decision tree before writing any code.