# /interview-me: Find out what you actually want before anything is built

Source: https://trendhub.net/skills/addyosmani-agent-skills/interview-me
Skill folder: https://github.com/addyosmani/agent-skills/tree/main/skills/interview-me
Pack: Addy Osmani's Agent Skills (https://trendhub.net/skills/addyosmani-agent-skills)
Works with: Claude Code, Any agent via the skills CLI, Codex, Gemini CLI, Antigravity CLI, Command Code

Interview-me makes the agent write its best guess of your goal with a confidence percentage, then ask one question at a time with its own guess attached. It probes answers that sound like best-practice talk, restates your intent including what is out of scope, and waits for a clear yes before stopping and offering next steps.

## When to use it

- A request like build me a dashboard leaves out who it is for, why, or what success means.
- Two reasonable goals pull against each other and you have not said which matters more.
- You ask the agent to grill you or stress-test your thinking before starting.

## How it works

1. **State a hypothesis**: The agent writes a one-sentence read of what you want plus an honest confidence number, with a note on what is missing when it is under about 70 percent.
2. **Ask singly with a guess**: It asks one focused question, adds its guessed answer and reasoning, and waits for your reaction before the next.
3. **Probe convention answers**: When you reply with words like scalable or the standard way, it asks what you would want if you did not have to justify it.
4. **Restate intent**: It writes back outcome, user, why now, success, constraint and out of scope in a few lines for you to correct.
5. **Confirm and stop**: It accepts only an explicit yes, then offers to save the intent, draft a spec or plan, and ends its turn without starting work.

## What it steers the agent away from

- Sending a batch of questions that invites skimmed answers
- Taking whatever you think is best as a decision
- Writing a spec or plan before you have confirmed the restated goal

## What it can touch

Conversation only; it may save the confirmed intent to docs/intent/ in your repo, but only after you agree.

## Pairs well with

- `/idea-refine`
- `/planning-and-task-breakdown`
- `/spec-driven-development`

## Questions

### When does the interview end?

When the agent can predict how you would answer its next three questions, or when several rounds pass without progress and it suggests stepping back.

### Can it run in an automated pipeline?

No. It needs a live person, so in CI or scheduled runs it reports the unclear request as a blocker instead of guessing.
