Is Interview Me free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Interview Me

Q: How do I know the Interview Me output is good?

The skill verifies itself against its own quality checks: Questions were asked one at a time, each shaped by the previous answer; The moment-of-use and success-definition questions were asked (or their answers were already known); The brief was played back and explicitly confirmed before production began; Every unresolved item appears in the assumption ledger, labelled.

🔵 Stable🕐 updated 2026-10-06 ✅ 3.3/5 🔷 SkillSpec L3 pm-method

Elicit the real requirements by interviewing the requester BEFORE building or writing anything — one question at a time, until the brief is buildable. Use when a request is vague ('make me a dashboard', 'write something for the board'), when past deliverables missed the mark, or when the user says 'interview me' / 'ask me questions first'. Produces a validated brief: goal, audience, constraints, success criteria, and explicit non-goals — then, and only then, the work.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Interview me before you build anything.”“Ask me questions first.”“Make me a dashboard.”“Work out what I actually need.”

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Questions were asked one at a time, each shaped by the previous answer

✓The moment-of-use and success-definition questions were asked (or their answers were already known)

✓The brief was played back and explicitly confirmed before production began

✓Every unresolved item appears in the assumption ledger, labelled

✓The interview stopped when answers stopped changing the build — no ritual questioning

⚠️ What it refuses to do

Do not fire a questionnaire — seven questions at once produces skim-answers and resentment

Do not interview when the brief is already clear — process applied without judgment is friction

Do not ask questions whose answers wouldn't change the deliverable — every question spends the requester's patience

Do not start building mid-interview "to save time" — half-brief work anchors the requester to the wrong draft

Do not skip the playback — the interview's value is captured only when the requester says "yes, that"

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="interview-me"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Interview Me is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog