Interview questions about what they did, not what they think.
A 30 minute guide for customer interviews with a screener, story questions, follow-up probes, and a close, built around one decision.
Customers are polite. Ask whether they would use something and they say yes. Ask what they want and they invent a feature. Five interviews later you have compliments and nothing to act on.
Customer Interview Guide starts from the decision the calls must inform and drops every question that does not serve it. The core is a set of questions about the last specific time, each with a follow-up, and a final audit that rewrites or deletes anything hypothetical.
What it produces.
- →One-sentence statement of the decision the interviews will inform
- →A screening question and participant definition
- →Five to seven past-tense story questions, each with a follow-up probe
- →An opening and close you can read aloud
- ✦Founders preparing customer discovery calls
- ✦Marketers researching why people buy or cancel
- ✦Product people who want facts before changing a roadmap
- →customer-interview-guide.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →customer-interview-guide-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude produces a list of reasonable questions, many starting with would or do you think. This ties every question to a decision, keeps them to specific past events, and audits the final guide for any hypothetical you have to rewrite.
How is this different from a Tool?
Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.