What problem does it solve? Users often ask for what they think they should want rather than what they actually need, and agents silently fill in ambiguous requirements before any plan or code exists. This skill closes that gap by interviewing the user one question at a time until the underlying intent is confirmed, preventing costly rework from building the wrong thing. ## Core Features & Use Cases - Hypothesis-Driven Questioning: 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: Probes past convention-signaling answers ("scalable", "best practice") with questions like "what would you actually want if you didn't have to justify it?" - Confirmed Intent Output: Produces a structured restatement (Outcome, User, Why now, Success, Constraint, Out of scope) gated on an explicit yes, with a checkable stop condition based on predicting the user's next three reactions. - Use Case: A user says "build me a dashboard for our metrics." Instead of proposing chart libraries, the agent interviews and discovers the real need is a personal experiment tracker list, avoiding building the wrong artifact entirely. ## Quick Start Ask the agent to interview you one question at a time about what you actually want before it starts planning or writing any code.
