User ResearchInterview PrepProduct ManagementAI Agent Skill
discovery-interview-prep
Guides a PM through preparing discovery interview questions tied to a stated research goal, avoiding confirmation-biased questions.
Install Options
Install into Claude Code, Cursor, Codex, or Antigravity with:
$ npx skills add deanpeters/product-manager-skills@discovery-interview-prep
Real Work Situation Solved
Discovery interview coming up - what questions actually surface the real problem?
“You've got 30 minutes with one customer and a list of assumptions to test - what do you actually ask them?”
5-Step Action Framework
- 1Write your research goal as one sentence before drafting any question - anything that doesn't trace back to it gets cut.
- 2Ask about past behavior, not future intentions - "Tell me about the last time you..." beats "Would you use a feature that...".
- 3Avoid questions that can be answered with a nod - "Is pricing a problem?" gets a polite yes; "Walk me through your last renewal decision" gets a real answer.
- 4Never pitch the solution mid-interview - if the customer asks what you're building, deflect back to their problem until the interview ends.
- 5After each answer, ask one follow-up "why" or "what happened next" before moving on - the first answer is rarely the real one.
Before
"Would you use a feature that let you export this to Excel?"
After
"Walk me through the last time you needed this data outside the app - what did you do, and what took the longest?"
Related Course
AI Product Management
SKILL.md Source Instructions
SKILL.md • Read-only preview# Discovery Interview Prep Skill Design a tailored interview plan from a stated research goal and customer segment, producing a question framework that surfaces past behavior instead of confirmation bias.