interview-me

Extract true user intent through one-question-at-a-time interviews.

3|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/vtgiang-dotcom/Solo-Code-Harness --skill interview-me-vtgiang-dotcom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: interview-me
Source: https://github.com/vtgiang-dotcom/Solo-Code-Harness/tree/main/.gemini/antigravity/skills/interview-me
Command: npx skills add https://github.com/vtgiang-dotcom/Solo-Code-Harness --skill interview-me-vtgiang-dotcom

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. The approach prevents misaligned plans and rushed solutions.

Core Features & Use Cases

  • One-question-at-a-time interview cadence to surface true intent
  • Attached, explicit GUESS prompts to accelerate alignment
  • Clear restates of intent for downstream planning and validation

Quick Start

Begin with an underspecified request and start the one-question-at-a-time interview to uncover the true intent.

Frequently Asked Questions about interview-me

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

FAQPage Schema
How do I clarify underspecified product management requests?

To clarify underspecified product management requests, this Skill conducts a one-question-at-a-time interview to extract true user intent, maintaining a confidence score until it reaches roughly 95% certainty about the underlying goal.

What is the best way to gather requirements when a user asks to build something without context?

The best way to gather requirements for contextless requests is a one-question-at-a-time interview using a hypothesis-and-GUESS mechanism, which surfaces the who, why, and success criteria to prevent misaligned plans.

How does an intent interview reach high confidence for downstream planning?

An intent interview reaches high confidence by asking clarifying questions sequentially and generating explicit GUESS prompts to accelerate alignment, concluding with a concise restatement of intent for downstream planning.

Can I use one-question interviews to stimulate thinking for vague feature requests?

Yes, you can use one-question interviews to stimulate thinking for vague feature requests by triggering the interview mechanism, which actively surfaces true intent rather than what the user thinks they should want.

When should I not use a one-question-at-a-time interview approach?

You should not use a one-question-at-a-time interview approach if the original request is already well-specified with clear who, why, and success criteria, as the mechanism is specifically designed for underspecified asks.