Structured intent extraction before specs, plans, or code. Complements clarify-underspecified with a stricter one-question cadence and explicit stop conditions.
When to use
User has a goal but not a spec
Multiple interpretations exist and batch questions would overwhelm
Before spec-driven-development or planning-and-task-breakdown
When not to use
User already provided a complete spec or ticket
Single factual question suffices
Emergency fix with clear repro steps
Workflow
State purpose — one sentence on what you are extracting (goal, constraints, success criteria).
Ask one question — highest-leverage unknown only; offer 2–4 concrete options when helpful.
Listen and summarize — after each answer, one-line recap of what you learned.
Stop when — you can write: objective, non-goals, constraints, acceptance criteria, and open risks.
Hand off — produce a short intent brief or propose spec-driven-development.
Rules
Never ask more than one question per turn unless user explicitly requests a batch.
Prefer multiple-choice or examples over open-ended vagueness.
Do not start implementation until stop condition is met or user waives interview.
Flag assumptions explicitly; do not silently fill gaps.
If user jumps to implementation, pause and confirm intent or non-goals in one question.
1---2name: interview-me-23description: Interview Me4---56# Interview Me78Structured intent extraction before specs, plans, or code. Complements `clarify-underspecified` with a stricter one-question cadence and explicit stop conditions.910## When to use1112- User has a goal but not a spec13- Multiple interpretations exist and batch questions would overwhelm14- Before `spec-driven-development` or `planning-and-task-breakdown`1516## When not to use1718- User already provided a complete spec or ticket19- Single factual question suffices20- Emergency fix with clear repro steps2122## Workflow23241. **State purpose** — one sentence on what you are extracting (goal, constraints, success criteria).252. **Ask one question** — highest-leverage unknown only; offer 2–4 concrete options when helpful.263. **Listen and summarize** — after each answer, one-line recap of what you learned.274. **Stop when** — you can write: objective, non-goals, constraints, acceptance criteria, and open risks.285. **Hand off** — produce a short intent brief or propose `spec-driven-development`.2930## Rules3132- Never ask more than one question per turn unless user explicitly requests a batch.33- Prefer multiple-choice or examples over open-ended vagueness.34- Do not start implementation until stop condition is met or user waives interview.35- Flag assumptions explicitly; do not silently fill gaps.36- If user jumps to implementation, pause and confirm intent or non-goals in one question.3738## Output template3940```markdown41## Intent brief42- **Objective:**43- **Non-goals:**44- **Constraints:**45- **Success criteria:**46- **Open risks:**47- **Next step:** spec / plan / spike / implement48```4950## Related skills5152- `clarify-underspecified` — quick minimum questions53- `idea-refine` — divergent exploration before intent lock54- `spec-driven-development` — after intent is clear5556*Adapted from [addyosmani/agent-skills](https://github.com/addyosmani/agent-skills) and [obra/superpowers](https://github.com/obra/superpowers) (MIT).*
Run npx skillmds@latest add charlieviettq/interview-me-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Interview Me It is listed under Productivity on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
charlieviettq (@charlieviettq) published this skill. Their other Agent Skills are listed on their SkillMD profile.