agentleFS
yuusakuriyuusakuri/agent-skills/skills/interview-script/SKILL.md

interview-script

Skill2 starsChanged 10 days agoMITView on GitHub

Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a structured interview script that surfaces real insights, not just opinions.

    line 8
  2. Distinctive:

    If the user provides files (personas, hypothesis lists, product briefs, or previous interview notes), read them first.

    line 18
  3. Distinctive:

    Ask permission to record (if applicable)

    line 32
  4. Distinctive:

    Use these when you hit an interesting thread:

    line 62
  5. Distinctive:

    Ask about their life, not your idea

    line 70
  6. Distinctive:

    Ask about the past, not the future ("Would you use X?" is useless)

    line 71
  7. Distinctive:

    Look for strong emotions — they signal real pain or delight

    line 74

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Customer Interview Script

Create a structured interview script that surfaces real insights, not just opinions. Follows "The Mom Test" principles — ask about their life, not your idea.

Domain Context

Customer interviews are one source in Stage 1 (Explore) of continuous discovery. Other sources: stakeholder interviews, usage analytics, data analytics, surveys, market trends, SEO/SEM analysis. The PM needs direct access to users, stakeholders, engineers, and designers — "without proxies." The Product Trio (PM + Designer + Engineer — Teresa Torres) should work together on discovery, not just the PM alone.

Context

You are preparing a customer interview script for research on $ARGUMENTS.

If the user provides files (personas, hypothesis lists, product briefs, or previous interview notes), read them first.

Instructions

  1. Clarify research objectives:
    • What specific questions does the team need answered?
    • What decisions will this research inform?
    • What assumptions need validation?
  2. Create the interview script with these sections:

    Opening (2-3 min)

    • Introduce yourself and the purpose (learning, not selling)
    • Set expectations: "There are no right or wrong answers. We're here to learn from your experience."
    • Ask permission to record (if applicable)
    • Confirm time available

    Warm-Up: Context & Background (5 min)

    • "Tell me about your role and what a typical day/week looks like."
    • "How long have you been doing [activity related to the product area]?"
    • Goal: Build rapport and understand their context

    Core Exploration: Jobs to Be Done (15-20 min)

    Current situation and behavior (past tense, specific instances):

    • "Walk me through the last time you [did the thing we're exploring]. What happened?"
    • "What tools or methods did you use?"
    • "How long did it take? Who else was involved?"

    Pain points and frustrations (observe, don't lead):

    • "What was the hardest part about that?"
    • "If you could wave a magic wand, what would change?"
    • "What have you tried to solve this? What happened?"

    Desired outcomes (their words, not yours):

    • "What does 'good' look like for you in this area?"
    • "How would you know if this was working well?"

    Willingness to pay / priority (skin in the game):

    • "How much time/money do you currently spend on this?"
    • "Have you looked for a better solution? What did you find?"
    • "What would you give up to have this solved?"

    Probing Techniques

    Use these when you hit an interesting thread:

    • "Tell me more about that" — opens up any topic
    • "Why?" (asked gently, 2-3 times) — gets to root causes
    • "Can you give me a specific example?" — moves from opinions to facts
    • "What happened next?" — follows the story
    • "How did that make you feel?" — captures emotional intensity

    The Mom Test Rules

    • Ask about their life, not your idea
    • Ask about the past, not the future ("Would you use X?" is useless)
    • Talk less, listen more — aim for 80/20 split
    • Never pitch during the interview
    • Look for strong emotions — they signal real pain or delight
    • Compliments are noise — "That sounds cool!" tells you nothing

    Wrap-Up (3-5 min)

    • "Is there anything I didn't ask that you think is important?"
    • "Who else should I talk to about this?"
    • Thank them for their time
    • Share next steps (if any)
  3. Customize the script: Adapt questions to the specific product area, persona, and research objectives. Add or remove sections based on the interview length available.
  4. Include a note-taking template:
    Participant: [Name / ID]
    Date: [Date]
    Key Jobs: [What they're trying to accomplish]
    Current Solution: [What they use today]
    Biggest Pain: [Their #1 frustration]
    Desired Outcome: [What success looks like]
    Willingness to Pay: [How much they invest / would invest]
    Surprise Finding: [Something unexpected]
    Follow-up: [Next steps]

Save as markdown. Include both the script and the note-taking template.


Further Reading

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.