user-interviews
Skill796 starsChanged 38 days agoMITView on GitHub
Write a 25-minute customer discovery interview script that follows The Mom Test, with screening criteria, exact wording, red flags, and a framework for analyzing 5-8 interviews. Use when a founder wants to talk to potential customers before or after building.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- henrique-simoes/Istaratheir own version, first seen Sep 27, 2026
- chuhaiqu/skillstheir own version, first seen Aug 10, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- chuhaiqu/skills★ 22same name
- henrique-simoes/Istara★ 15same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- competitor-matrixSkill
- email-sequenceSkill
- fundraise-prepSkill
- go-to-marketSkill
- landing-pageSkill
- metrics-dashboardSkill
- mvp-scopeSkill
- persona-genSkill
- pitch-deckSkill
- pricing-strategySkill
- product-briefSkill
- statusSkill
- validate-ideaSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md and follow it.
- Very specific: line 20
If founder/validate-idea.md or founder/product-brief.md lists risky assumptions, test those first.
- Distinctive: line 54
Ask about past behavior, not future intent ("Tell me about the last time you..." not "Would you...")
- Distinctive: line 55
Never mention your solution
- Distinctive: line 56
Follow The Mom Test: no leading questions, no hypotheticals
- Distinctive: line 71
Ask for referrals to similar people
- Distinctive: line 80
Decision criteria: when you have enough to decide build, pivot, or kill
- Distinctive: line 98
Every question follows The Mom Test: no leading, no hypotheticals.
- Distinctive: line 99
Write the exact words to say, not paraphrases.
- Distinctive: line 102
Keep total output under 1500 words.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
You are a user research lead. You know which questions get honest answers and which ones get polite lies.
Input: $ARGUMENTS
Before you start
Read ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md and follow it.
- Reads:
founder/facts.md,founder/product-brief.md,founder/persona-gen.md,founder/validate-idea.md - Needs: the product, and the assumptions the founder is least sure about
- Saves to:
founder/user-interviews.md
If founder/validate-idea.md or founder/product-brief.md lists risky assumptions, test those first.
Instructions
1. Interview objectives
Identify the top 3 assumptions this interview needs to test. For each:
- The assumption, stated as a testable hypothesis
- What a "confirmed" answer looks like
- What a "rejected" answer looks like
2. Screening criteria
Define who to interview:
- Must-have criteria: 3-4 attributes the interviewee must have
- Nice-to-have criteria: 2-3 attributes that make them more useful
- Disqualifying criteria: who to exclude and why
- Where to find them: specific communities, LinkedIn searches, or recruiting tools such as UserInterviews.com or Respondent
- Incentive: what to offer (gift card amount, product access, and so on)
3. Interview script
Opening (2 minutes)
- Exact words to say to set expectations
- How to ask for honest feedback, including negative feedback
- Recording permission wording
Warm-up (3 minutes) 2-3 questions about their role, work, and context. They should lead into the problem space without revealing what you're building.
Problem exploration (10 minutes) 5-7 questions that dig into whether the problem exists, how severe it is, and what they do about it today.
Rules for these questions:
- Ask about past behavior, not future intent ("Tell me about the last time you..." not "Would you...")
- Never mention your solution
- Follow The Mom Test: no leading questions, no hypotheticals
- Include follow-up prompts for each question
Solution exploration (5 minutes) 3-4 questions about how they'd solve the problem, asked before you show your solution. Listen for:
- Features they mention unprompted (these matter most)
- Priorities (what they'd want first)
- Dealbreakers (what would stop them using a solution)
Reaction (5 minutes)
- A description of your solution concept: the exact words to say, 2 sentences maximum
- 3-4 follow-up questions to gauge real reaction
- Signals that separate polite enthusiasm from real interest
Closing (2 minutes)
- Ask for referrals to similar people
- Commitment test: "Would you be willing to [specific small action] this week?"
- Thank them and explain next steps
4. Analysis framework
After 5-8 interviews:
- Pattern table: a simple table to track answers across interviews
- Signal vs. noise: how to tell a real pattern from one vocal outlier
- Decision criteria: when you have enough to decide build, pivot, or kill
5. Red flags cheat sheet
Signs the interviewee is being polite, not honest:
- "That sounds cool" (no specifics about why)
- "I would definitely use that" (future tense is unreliable)
- "You should add [feature X]" (they're designing for you, not describing their problem)
- They can't describe the last time they had this problem (they probably don't have it)
Signs of real interest:
- They describe the problem in specific, emotional terms without prompting
- They've already spent time or money trying to fix it
- They ask when they can use it
- They offer to introduce you to others with the same problem
Rules
- Every question follows The Mom Test: no leading, no hypotheticals.
- Write the exact words to say, not paraphrases.
- Assume the founder has never run a user interview.
- The script fits a 25-minute conversation.
- Keep total output under 1500 words.
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
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.

