addy-interview-me

Extracts underlying user intent through one-question-at-a-time interviews before planning or coding.

Updated Aug 21, 2026
One-click install
npx skills add https://github.com/TylerSimons1127/vibe --skill addy-interview-me-tylersimons1127
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: addy-interview-me
Source: https://github.com/TylerSimons1127/vibe/tree/main/skills/addy-interview-me
Command: npx skills add https://github.com/TylerSimons1127/vibe --skill addy-interview-me-tylersimons1127

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 agents silently fill in ambiguous requirements. This Skill closes that gap before any plan, spec, or code exists, when switching costs are still zero. ## Core Features & Use Cases - Hypothesis-Driven Interviewing: States a one-sentence hypothesis with an honest confidence number, then asks one focused question at a time with a guess attached so users can react instead of generating answers from scratch. - Want vs. Should-Want Detection: Probes sophistication-signaling answers ("scalable", "clean", "modern") with the question "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 95% confidence stop test. - Use Case: A user says "build me a dashboard for our metrics." Instead of proposing chart libraries, the agent interviews and discovers the real ask is a personal experiment tracker list — a different artifact entirely. ## Quick Start Say "interview me before we start" or "stress-test my thinking on this request" and the agent will ask one question at a time until it can confirm what you actually want.

Frequently Asked Questions about addy-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 to the next three questions, then restate the intent for explicit confirmation.

When should I use requirements interviewing versus writing a spec directly?▼

Interview first when the ask is missing who the user is, why they want it, what success looks like, or the binding constraint. Write the spec only after the user explicitly confirms a restated intent, since specs consume the intent this process produces.

Can this interview process run in CI pipelines or autonomous loops?▼

No. The skill requires a live, responsive user and must not be invoked in non-interactive contexts like CI pipelines, scheduled runs, or autonomous loops. In those contexts, flag underspecified asks as blockers instead of guessing.

Why ask one question at a time instead of a batch of questions?▼

Batched questions encourage skim-reading and surface answers, and later questions often depend on earlier answers. One at a time lets the user react to your hypothesis, keeps framing correct, and spends their limited attention efficiently.

What counts as confirmation that requirements are understood?▼

Only an explicit yes to a concrete restatement counts. "Whatever you think", "sounds good", or silence are not confirmation — they signal delegation or disengagement and require re-asking with concrete options or a refined restate.

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 over verification. Also skip it when you already have roughly 95% confidence.