What problem does it solve? Users often ask for what they think they should want rather than what they actually need, leading to misaligned specs, plans, and code. This Skill closes the gap between the stated ask and the real intent before any building begins, when changing direction costs nothing. ## Core Features & Use Cases - Hypothesis-Driven Interviewing: States a one-sentence hypothesis with an explicit confidence number, then asks one focused question at a time with a guess attached so the user can react instead of generating answers from scratch. - Want vs. Should-Want Detection: Identifies convention-signaling and sophistication-signaling answers ("scalable", "best practice") and probes what the user would want if they didn't have to justify it. - Confirmed Intent Output: Produces a structured restatement (Outcome, User, Why now, Success, Constraint, Out of scope) that requires an explicit yes before any downstream spec or plan is written. - Use Case: A user says "build me a dashboard for our metrics." Instead of proposing chart libraries, the Skill interviews and discovers the real need is a personal experiment tracker list, avoiding building the wrong artifact entirely. ## Quick Start Ask the AI to interview you about your request before it starts planning, for example by saying "interview me before we start building this."
