From faos-pm
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->
npx claudepluginhub frank-luongt/faos-skills-marketplace --plugin faos-pmThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.
Create structured, bias-free customer interview scripts that uncover real needs — not just what people say they want.
Most customer interviews produce unusable data because they ask leading questions, talk about the future ("Would you use X?"), or let the interviewer pitch instead of listen. This skill produces scripts grounded in The Mom Test principles: talk about their life, not your idea.
Set the stage and build rapport.
"Thanks for taking the time to chat with me today. I'm [name] from [company].
We're researching [broad topic area] to understand how people like you
handle [relevant activity]. There are no right or wrong answers — I'm
genuinely interested in your experience.
Is it okay if I take notes? [And record, if applicable]
Before we dive in, could you tell me a bit about your role and what
a typical day/week looks like for you?"
Rules:
Understand their context and establish baseline.
Template questions:
Purpose: Build rapport, understand their world, identify context that shapes their needs.
This is where you dig into past behavior and real experiences. Follow Mom Test rules.
Close gracefully and leave the door open.
"This has been really helpful. A couple of quick closing questions:
- Is there anything about [topic] that I should have asked but didn't?
- Is there anyone else you'd recommend I talk to about this?
Thank you so much for your time. I may follow up with a quick question
or two — would that be okay?"
Use these when an answer is vague or surface-level:
| Technique | Example |
|---|---|
| "Tell me more" | "That's interesting — can you tell me more about that?" |
| Laddering (Why x3) | "Why was that frustrating?" → "Why does that matter?" → "Why is that important to your work?" |
| Specific example | "Can you give me a specific example of when that happened?" |
| Contrast | "How is that different from how you did it before?" |
| Quantify | "How often does that happen? How much time does it take?" |
| Emotional | "How did that make you feel?" |
After each interview, capture:
## Interview Notes
**Date**: [date]
**Participant**: [name/role/company]
**Interviewer**: [name]
### Key Jobs (What they're trying to accomplish)
1. [job]
2. [job]
### Current Solution
- [How they solve it today]
### Biggest Pain Points
1. [pain] — Severity: High/Medium/Low
2. [pain] — Severity: High/Medium/Low
### Desired Outcome
- [What "success" looks like to them]
### Willingness to Pay / Priority
- [Evidence of how much they care]
### Surprise Findings
- [Anything unexpected]
### Verbatim Quotes (Most Important)
- "[exact quote]"
- "[exact quote]"
### Follow-Up Actions
- [ ] [action]
| Avoid | Why | Instead |
|---|---|---|
| "Would you use X?" | Hypothetical = unreliable | "Tell me about the last time you tried to solve this" |
| Pitching your solution | Biases all subsequent answers | Save pitching for after the interview |
| Leading questions | Confirms your bias, not their reality | Ask open-ended, neutral questions |
| Multiple questions at once | Overwhelms, they answer the easiest one | One question at a time |
| Nodding/agreeing too much | Signals what you want to hear | Stay neutral, curious |
| Only interviewing fans | Selection bias | Include churned users, non-users, competitors' users |