customer-interviews
Skill46 starsChanged 4 months agoMITView on GitHub
Generates structured interview guides for five B2B SaaS research types: discovery, win/loss, churn, expansion,
4 other projects use a version of this.
Adopted by
Most recently taken up by
- brainbytes-dev/everything-claude-marketingtheir own version, first seen Nov 1, 2026
- menkesu/awesome-pm-skillstheir own version, first seen Oct 13, 2026
- RefoundAI/lenny-skillstheir own version, first seen Jul 15, 2026
- impactbrussels/FounderOStheir own version, first seen Jun 23, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- RefoundAI/lenny-skills★ 1.3ksame name
- menkesu/awesome-pm-skills★ 441same name
- brainbytes-dev/everything-claude-marketing★ 9same name
- impactbrussels/FounderOS★ 2same 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.
- brand-kitSkill
- company-contextSkill
- competitor-researchSkill
- expert-povSkill
- funnel-strategySkill
- icp-behaviouralSkill
- icp-researchSkill
- marketing-team-trackerSkill
- read-bookSkill
- signal-scanSkill
- tov-guidelinesSkill
- watch-videoSkill
- win-loss-analysisSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
6
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
- Distinctive: line 80
Run this checklist before every interview.
- Distinctive: line 117
Follow the energy: When they lean into a topic, go deeper.
- Distinctive: line 119
Use their words, not yours: Don't rephrase their pain into your product language.
- Distinctive: line 120
Sit in the silence: When they pause, don't fill the gap.
- Distinctive: line 125
Use these when an answer is surface-level:
- Distinctive: line 144
After the interview, map findings to these categories.
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
Customer interviews skill
Prepare structured interview guides for B2B SaaS customer research. Produces question banks, preparation frameworks, and synthesis templates that feed directly into ICP research and positioning work.
Inputs
| Input | Required | Source |
| Interview type | Yes | User specifies: discovery, win/loss, churn, expansion, or testimonial |
| Company context | Recommended | /company-context output or client CLAUDE.md |
| ICP profile | Recommended | /icp-research output |
| Specific research goals | Yes | User states what they're trying to learn |
Interview types
Full question banks (10-15 questions per type) live in the premium reference. Use this table to pick the right type, then pull 8-12 questions from the bank.
| Type | Purpose | When to use |
| 1. Discovery | Understand the prospect's world before they became a customer. Map pain, workflow, buying triggers, decision criteria. | Early-stage ICP research, entering new segments, validating positioning hypotheses |
| 2. Win/loss | Understand why deals closed (or didn't). Extract decision criteria, competitive dynamics, buying process details. | After closed-won/closed-lost deals, competitive positioning, sales enablement |
| 3. Churn | Understand why customers left. Identify product gaps, service failures, unmet expectations. | After churn events, retention strategy, product feedback loops |
| 4. Expansion | Understand what drives upsell, cross-sell, seat expansion. Map the internal champion's advocacy process. | Expansion playbook development, pricing research, PLG analysis |
| 5. Testimonial | Extract quotable results, transformation stories, social proof. | Case study production, social proof gathering, website copy refresh |
Preparation framework
Run this checklist before every interview.
1. Research the interviewee
- Role, title, tenure at company
- LinkedIn profile review (career path, posts, interests)
- Their company's stage, size, industry
- Any previous interactions with your team (sales notes, support tickets, NPS scores)
- Public content they've produced (blog posts, conference talks, comments)
2. Define research goals
- What are the 3 specific things you need to learn from this conversation?
- What hypotheses are you testing?
- What gaps in your current ICP/positioning/competitive data does this fill?
- How will you use the output? (Which downstream skill or deliverable?)
3. Customize the question bank
- Select 8-12 questions from the relevant interview type
- Reorder based on priority (most important questions early, in case you run short)
- Personalize with company-specific details ("I noticed you switched from [competitor]...")
- Prepare 2-3 follow-up probes for each key question
- Remove questions you already have answers to
4. Logistics
- Interview length: 30-45 minutes (never over 60)
- Recording permission: ask at the start, not mid-conversation
- Note-taker: assign someone or use transcription (Granola, Otter, etc.)
- Warm-up plan: 2-3 minutes of genuine rapport before questions
During the interview
Principles
- Listen more than you talk. Target 80/20 ratio (them/you).
- Follow the energy. When they lean into a topic, go deeper. Your script is a guide, not a cage.
- Ask "why" and "tell me more" liberally. The best insights come from the second and third layers.
- Use their words, not yours. Don't rephrase their pain into your product language.
- Sit in the silence. When they pause, don't fill the gap. They're often about to say the most honest thing.
- Capture exact quotes. Flag verbatim language in your notes with quotation marks. These are gold for messaging.
Follow-up prompts
Use these when an answer is surface-level:
- "Can you give me a specific example of that?"
- "What happened next?"
- "How did that make you feel?"
- "Who else was affected by that?"
- "What would have happened if you hadn't done anything?"
- "Help me understand the timeline on that."
- "You mentioned [X] -- say more about that?"
Red flags during interviews
- They're giving you the answers they think you want. Redirect with "I really want the honest version."
- They're speaking in generalities. Push for specifics: "When was the last time that happened?"
- They're selling you on their company. Gently steer back: "That's helpful context. Now tell me about the problem side."
- You're asking leading questions. Catch yourself. "Don't you think X is a problem?" becomes "How do you think about X?"
Synthesis framework
After the interview, map findings to these categories. Each one feeds directly into downstream skills.
| Category | Feeds into | What to capture |
| Pain points and triggers | icp-research, positioning | Specific problems described; what triggered the search; urgency / cost of inaction |
| Buying process | icp-research, win-loss-analysis | Who was involved; evaluation process; timeline and friction points |
| Decision criteria | positioning, product-messaging | What mattered most; deal-breakers; how alternatives were compared |
| Language and vocabulary | tone-of-voice, messaging | Exact phrases for the problem; how they describe the solution to peers; words they avoid |
| Results and impact | case-study, testimonial content | Quantifiable outcomes; qualitative changes; before/after contrast |
| Objections and concerns | sales-enablement, battlecards | What almost stopped them buying; concerns remaining; what they'd change |
Anti-patterns
Don't do these:
- Asking yes/no questions. Every question should be open-ended.
- Running through all 15 questions in 30 minutes. Pick 8-12 and go deep.
- Recording without permission. Always ask first, and respect a "no."
- Interviewing through a screen share of your product. This is research, not a demo.
- Combining interviews with sales pitches. Keep them separate or you'll poison the data.
- Interviewing only happy customers. Churned users and lost deals are where the real insights live.
- Skipping synthesis. Raw notes decay fast. Synthesize within 24 hours or the context fades.
- Treating one interview as truth. A single data point is an anecdote. You need 5-8 interviews per segment to see patterns.
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.