Product interview
Skill jpoindexter/product-management-skills/skills/product-interview
Plan, conduct, or analyze non-leading customer interviews that produce behavioral evidence. Use when the user needs an interview guide, wants to evaluate interview notes, must distinguish signal from compliments or hypothetical intent, or needs a recruiting and synthesis plan.From its SKILL.md
npx -y skills add jpoindexter/product-management-skills --skill product-interviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.7 KB, 480 tokens by cl100k_base, as published. Nobody here has run it
Product Interview
Collect specific evidence about a customer's recent behavior, constraints, alternatives, and commitments without pitching for approval.
Prepare
Define:
- Decision the interviews must inform
- Target participant and qualifying behavior
- Top three unknowns
- Evidence that would support, weaken, or invalidate each belief
- Note-taking and consent plan
Interview workflow
- Open with the participant's situation and most recent relevant episode.
- Reconstruct the sequence: trigger, action, tools, people, time, money, workarounds, and outcome.
- Ask for specific past examples before opinions or future intentions.
- Explore the cost and frequency of the problem and what happens when it remains unsolved.
- Ask how existing alternatives were selected, paid for, adopted, or abandoned.
- Surface decision participants, constraints, and switching friction.
- Avoid presenting the proposed solution until learning goals are complete.
- End with an evidence-producing next step when appropriate: introduction, artifact, trial, time commitment, or payment conversation.
Evidence coding
Classify each note as:
- Observed past behavior
- Current workflow or artifact
- Existing workaround or alternative
- Money, time, reputation, or access commitment
- Reported pain or preference
- Hypothetical intention
- Compliment
- Feature suggestion
Use the first four as stronger evidence. Preserve the rest as context, not validation.
Output contract
Return the interview objective, screener, guide, prohibited leading questions, note schema, evidence summary, contradictions, confidence, and next decision.
Quality gate
- Every key belief maps to a question or observable artifact.
- Questions are about the participant's life rather than the team's idea.
- The guide contains follow-ups for recency, frequency, severity, and workaround cost.
- Synthesis distinguishes participant count from evidence strength.
- The plan includes how negative or disconfirming evidence will be handled.
Avoid
- “Would you use...?” and “Do you like...?” as evidence
- Explaining the idea until the participant agrees
- Counting compliments as demand
- Pooling unlike customer segments
- Reporting themes without traceable notes
Source grounding
Operational synthesis informed by The Mom Test and the interview and story-mapping practices in Continuous Discovery Habits.
What ships with it: 1 file
212 B alongside SKILL.md
agents/
- openai.yaml212 B