agentleFS
Sign inStart free
zpower426zpower426/pmpowers/skills/user-interviewing/SKILL.md

user-interviewing

Skill0 starsChanged 7 months agoMITView on GitHub

Master the art of questioning, uncovering users' real Job-to-be-Done (JTBD) and latent pain points through structured interviews.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Before starting any interview, you must define "Interview Goals" and a "Hypothesis List." Evidence synthesis must be completed within 24 …

    line 11
  2. Distinctive:

    Every successful interview output must answer:

    line 47

≈ “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

User Interviewing: Professional Interviewing and Evidence Acquisition

Reject surface-level requests; seek the motivation behind real behaviors.

<HARD-GATE> Before starting any interview, you must define "Interview Goals" and a "Hypothesis List." Evidence synthesis must be completed within 24 hours after the interview ends. </HARD-GATE>

Checklist

  1. Define Interview Goals — What are we trying to learn through this interview? Which hypothesis are we validating?
  2. Screen Participants — Are they in the real scenario where the problem occurs?
  3. Draft Script — Use "The Mom Test" principles. Focus on past behavior rather than future promises.
  4. Execute & Capture — Record key raw dialogues in docs/pmpowers/discovery/.
  5. Synthesize Evidence — Extract Pains, Gains, and JTBDs.

Interview Guidance Flow

digraph interview_flow {
    "Set Context" [shape=box];
    "Review Recent Events" [shape=box];
    "Deep Dive Motivation (5 Whys)" [shape=box];
    "Explore Alternatives" [shape=box];
    "Summary & Thanks" [shape=box];

    "Set Context" -> "Review Recent Events";
    "Review Recent Events" -> "Deep Dive Motivation (5 Whys)";
    "Deep Dive Motivation (5 Whys)" -> "Explore Alternatives";
    "Explore Alternatives" -> "Summary & Thanks";
}

Red Flags (Anti-Patterns)

  • Hypothetical Questions: "Would you use this feature?" (❌) -> Instead: "What did you do the last time you encountered this problem?" (✅)
  • Multiple Questions: Throwing three questions at once. (❌)
  • Selling Solutions: The interview turns into your product demo session. (❌)

Expert Principles: JTBD Capture

Every successful interview output must answer:

  • Trigger: What event prompted the user to start looking for a solution?
  • Friction: What difficulties did the user encounter when trying to solve it?
  • Reward: What does the standard for success look like in the user's mind?

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.

Check your setup, free