interview-me

Extracts underlying user intent through one-question-at-a-time interviews until 95% confidence.

2|Updated Jul 1, 2026
One-click install
npx skills add https://github.com/Lazare-Panam/mars-api --skill interview-me-lazare-panam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: interview-me
Source: https://github.com/Lazare-Panam/mars-api/tree/main/Mars.API/.claude/skills/interview-me
Command: npx skills add https://github.com/Lazare-Panam/mars-api --skill interview-me-lazare-panam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Users often ask for what they think they should want rather than what they actually need, and building on those unstated assumptions locks in the wrong solution. This Skill closes the gap between the stated ask and the real intent before any plan, spec, or code exists. ## 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 Detection: Identifies convention-driven or sophistication-signaling answers ("scalable", "best practice") and probes what the user would want without justification. - Confirmed Intent Output: Produces a structured restatement (Outcome, User, Why now, Success, Constraint, Out of scope) gated on an explicit yes, with optional persistence to docs/intent/. - Use Case: A user says "build me a dashboard for our metrics." Instead of proposing chart libraries, the Skill interviews them and discovers the actual need is a personal experiment tracker list, avoiding building the wrong artifact. ## Quick Start Ask the AI to interview you about your request before writing any plan or code, for example by saying "interview me about this feature idea before we start."

Frequently Asked Questions about interview-me

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clarify vague feature requests before writing code?

State a one-sentence hypothesis with a confidence number, then ask one focused question at a time with your best guess attached. Continue until you can predict the user's reactions, then restate the intent covering outcome, user, success criteria, and out-of-scope items for explicit confirmation.

How to run a requirements interview with a stakeholder?

Ask one question at a time rather than batching, attach your hypothesis to each question so the stakeholder can react quickly, and watch for convention-driven answers like "best practice" or "scalable." End with a structured restatement they must explicitly confirm.

When should I not use an intent-clarification interview?

Skip it for unambiguous self-contained asks like renames or typo fixes, pure information requests, mechanical operations, or when the user explicitly prioritizes speed. It also requires a live responsive user, so it does not work in CI pipelines or autonomous runs.

Why does asking multiple questions at once fail in requirements gathering?

Batched questions encourage skim-reading and surface answers, and later questions often depend on earlier answers, locking in wrong framing. One question at a time with an attached guess lets the user react to a concrete hypothesis instead of generating answers from scratch.

What counts as confirmation of user intent?

Only an explicit yes to a concrete restatement counts. Responses like "whatever you think is best," "sounds good," or silence are delegation or polite exits, not confirmation, and require re-asking with concrete options or a refined restatement.