Help us improve
Share bugs, ideas, or general feedback.
Coach PM candidates through product-sense interviews with a six-part answer spine: clarify, rationale, goal, segmentation, pain points, and solution. Prevents solution-jumping and produces crisp spoken answers.
npx claudepluginhub deanpeters/product-manager-skills --plugin workshop-facilitationHow this skill is triggered — by the user, by Claude, or both
Slash command
/product-manager-skills:product-sense-interview-answerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Help PM candidates and interview coaches structure product-sense answers that sound strong out loud, not just on paper. Use this when practicing prompts like "How would you improve X?", "Design a product for Y", or "What would you build next for Z?"
Brainstorms product ideas, explores problem spaces, challenges assumptions, and stress-tests concepts as a PM thinking partner. Use for new opportunities, product problem-solving, or idea validation.
Guides greenfield product ideas from raw concept to structured product-concept.md via conversation, capturing vision, core experience, target users, trust model, platforms, and scope.
Guides interactive product discovery sessions as CPO persona through 20 questions on foundation, market, strategy, and technical context. Saves responses and generates strategy docs.
Share bugs, ideas, or general feedback.
Help PM candidates and interview coaches structure product-sense answers that sound strong out loud, not just on paper. Use this when practicing prompts like "How would you improve X?", "Design a product for Y", or "What would you build next for Z?"
This is not a memorize-and-recite script. It is a reasoning scaffold that prevents solution-jumping, forces real prioritization, and leaves the interviewer with a clean story they can follow.
Strong product-sense answers do more than generate ideas. Interviewers are usually testing whether you can:
The order matters. If you skip from prompt to feature ideas, your answer sounds clever but ungrounded. If you establish the user, goal, and pain first, your solution feels earned.
Use template.md as the working structure.
Start by surfacing the two ambiguities that change the answer most. Good clarifiers usually narrow:
If the interviewer does not answer, state your assumptions and move on. The goal is to unblock the rest of the answer, not to turn the interview into requirements gathering.
Quality bar: Ask questions that materially change the solution. "Are we talking mobile or desktop?" matters less than "Are we optimizing for viewers, creators, or advertisers?"
Explain why the space matters now.
For the market view, cover:
If a company is named, then add:
End this section with a one-line thesis. That thesis should make the rest of the answer feel inevitable.
Quality bar: Use qualitative signals unless you know the numbers cold. Fake precision is worse than grounded judgment.
Write one sentence in this format:
Help [user] [achieve outcome], so that [broader impact].
Then describe what success looks like for the user in observable terms.
Good: "Help beginner YouTube learners find content they are glad they watched, so that the platform becomes an intentional learning destination."
Bad: "Build a personalized AI learning path feature." That is a solution disguised as a goal.
Do not jump straight to persona. First identify the ecosystem players, then choose the player you want to serve. After that, choose two segmentation dimensions that actually change needs.
Good segmentation dimensions usually change:
Weak dimensions are often demographic cuts that do not change the product meaningfully.
After choosing your target segment:
Break the user journey into 4-6 stages. Then list the frictions across that journey.
Prioritize the top pain point using:
This is the fulcrum of the entire answer. If the pain point is vague or weak, the solution section becomes generic.
Quality bar: Pain points should describe user friction, not missing features. "No structured progression after each video" is a pain. "No AI learning path" is already a solution.
List three distinct solutions. They should solve the same pain in different ways, not represent three feature line-items inside one idea.
Evaluate each option on:
Then choose one MVP and specify:
Close with a one-sentence recap that names:
That final sentence is what the interviewer should remember.
See examples/improve-youtube.md for a full worked example.
What makes it strong:
A strong answer to this prompt would explicitly state a startup assumption if no company is named, prioritize people who live alone, and choose the wake-up problem before discussing dispatch or smart-home integrations.
What makes this example useful:
"I would improve YouTube by adding AI summaries, better recommendations, creator analytics, and a study mode."
Why this fails:
This kind of answer can sound energetic in the moment, but it signals weak PM judgment.
template.mdexamples/improve-youtube.mdskills/problem-statement/SKILL.mdskills/proto-persona/SKILL.mdskills/customer-journey-map/SKILL.mdskills/opportunity-solution-tree/SKILL.md