agentleFS
zpower426zpower426/pmpowers/skills/customer-discovery/SKILL.md

customer-discovery

Skill0 starsChanged 7 months agoMITView on GitHub

Understand user personas, pain point scenarios, and their underlying JTBD (Job-to-be-Done) through structured research interviews. Ensure evidence authenticity before defining any solution.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Deep Dive Motivation (Five Whys): Ask why repeatedly until you touch on the user's emotional motivation or efficiency bottleneck.

    line 28
  2. Distinctive:

    Every research output must be able to fill the following formula:

    line 32

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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 Discovery: Deep User Discovery and Evidence Synthesis

Reject product definitions based on assumptions. Uncover real user behavioral motivations through deep interviews and observations, and transform them into quantifiable "opportunities."

Checklist

  1. Identify Target Segments — Who is the person in the most pain right now? Define their characteristics, scenarios, and existing alternatives.
  2. Design Non-Leading Interview Protocols — Use the "Past behavior predicts future behavior" principle. Write questions that focus on specific events rather than hypothetical intentions.
  3. Execute & Capture Raw Evidence — Save raw dialogue records or key summaries to docs/pmpowers/discovery/.
  4. Synthesize Evidence — Extract core pain points, unmet needs, and potential JTBDs.
  5. Sync Opportunity Map — Connect synthesized insights to nodes in opportunity-mapping.

Interview Guidance: The Mom Test Protocol

1. Anti-Patterns

  • Asking about Future Intent: "If you had this feature, would you use it?" (❌) -> People will lie out of politeness.
  • Leading Bias: "Don't you think the current process is cumbersome?" (❌) -> Guiding the user to give the answer you want.
  • Selling Solutions: Strictly forbid mentioning your product ideas during the first 90% of the interview. (❌)

2. Best Practices

  • Anchor Specific Events: "When was the last time you encountered [Problem]? Please walk me through that process." (✅)
  • Dig for Alternatives: "How much money or time do you currently spend to solve this? What tools have you tried?" (✅)
  • Deep Dive Motivation (Five Whys): Ask why repeatedly until you touch on the user's emotional motivation or efficiency bottleneck. (✅)

Core Framework: JTBD (Job-to-be-Done)

Every research output must be able to fill the following formula:

"When I am in [Scenario], I want to [Take Some Action], so that I can [Achieve Some Progress/Outcome]."

Delivery Standards

Interview records and synthesis reports must be stored in docs/pmpowers/discovery/YYYY-MM-DD-<user-or-segment>.md.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.