Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/phuryn-interview-script/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 73% | 0% |
Create a structured interview script that surfaces real insights, not just opinions. Follows "The Mom Test" principles — ask about their life, not your idea.
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.
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.
### Opening (2-3 min)
### Warm-Up: Context & Background (5 min)
### Core Exploration: Jobs to Be Done (15-20 min)
Current situation and behavior (past tense, specific instances):
Pain points and frustrations (observe, don't lead):
Desired outcomes (their words, not yours):
Willingness to pay / priority (skin in the game):
### Probing Techniques Use these when you hit an interesting thread:
### The Mom Test Rules
### Wrap-Up (3-5 min)
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.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,097 | 27,059 | +68% | 1 | 1 | 0% | 2,814 | 4,719 | +68% | 0 | 0 | — |
case-02 | fail→fail | 20,019 | 20,728 | +4% | 1 | 1 | 0% | 3,012 | 4,589 | +52% | 0 | 0 | — |
case-03 | fail→pass | 14,190 | 20,005 | +41% | 1 | 1 | 0% | 2,500 | 4,454 | +78% | 0 | 0 | — |
case-04 | pass→fail | 9,703 | 16,939 | +75% | 1 | 1 | 0% | 1,860 | 4,078 | +119% | 0 | 0 | — |
case-05 | pass→fail | 21,337 | 17,947 | -16% | 1 | 1 | 0% | 4,007 | 4,044 | +1% | 0 | 0 | — |
case-06 | pass→pass | 16,790 | 18,871 | +12% | 1 | 1 | 0% | 3,373 | 5,286 | +57% | 0 | 0 | — |
case-07 | pass→pass | 18,683 | 25,863 | +38% | 1 | 1 | 0% | 2,561 | 4,787 | +87% | 0 | 0 | — |
case-21 | pass→pass | 18,656 | 18,664 | +0% | 1 | 1 | 0% | 2,979 | 3,755 | +26% | 0 | 0 | — |
case-08 | fail→pass | 24,118 | 21,397 | -11% | 1 | 1 | 0% | 2,963 | 4,710 | +59% | 0 | 0 | — |
case-09 | fail→fail | 12,700 | 15,021 | +18% | 1 | 1 | 0% | 2,176 | 3,517 | +62% | 0 | 0 | — |
case-10 | fail→fail | 18,744 | 14,508 | -23% | 1 | 1 | 0% | 2,447 | 3,558 | +45% | 0 | 0 | — |
case-11 | fail→pass | 11,301 | 13,876 | +23% | 1 | 1 | 0% | 1,974 | 3,501 | +77% | 0 | 0 | — |
case-12 | fail→fail | 4,148 | 8,767 | +111% | 1 | 1 | 0% | 760 | 2,621 | +245% | 0 | 0 | — |
case-13 | fail→fail | 16,174 | 16,515 | +2% | 1 | 1 | 0% | 2,175 | 3,855 | +77% | 0 | 0 | — |
case-14 | fail→fail | 15,238 | 13,393 | -12% | 1 | 1 | 0% | 2,062 | 3,597 | +74% | 0 | 0 | — |
case-15 | fail→pass | 15,712 | 22,642 | +44% | 1 | 1 | 0% | 2,827 | 4,264 | +51% | 0 | 0 | — |
case-16 | fail→pass | 13,681 | 21,754 | +59% | 1 | 1 | 0% | 2,398 | 4,160 | +73% | 0 | 0 | — |
case-17 | fail→fail | 11,972 | 17,778 | +48% | 1 | 1 | 0% | 1,932 | 4,018 | +108% | 0 | 0 | — |
case-18 | pass→pass | 13,162 | 16,965 | +29% | 1 | 1 | 0% | 2,644 | 3,845 | +45% | 0 | 0 | — |
case-19 | pass→pass | 15,274 | 24,635 | +61% | 1 | 1 | 0% | 2,523 | 4,617 | +83% | 0 | 0 | — |
case-20 | fail→pass | 19,764 | 21,536 | +9% | 1 | 1 | 0% | 2,543 | 4,039 | +59% | 0 | 0 | — |
case-22 | pass→pass | 16,874 | 20,679 | +23% | 1 | 1 | 0% | 2,760 | 4,788 | +73% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.