← ClaudeAtlas

pm-customer-interview-coachlisted

Plan, critique, or stress-test a customer-discovery interview against the Mom Test rules. Use when the user is preparing an interview script, reviewing a transcript, debriefing what they "learned," or deciding what to do with a batch of customer conversations. Catches leading questions, fluff-inducing phrasing, compliments mistaken for data, premature zoom into a hypothesized problem, and missed commitment asks. Returns a question-by-question rewrite, a list of what was actually learned vs. imagined, and the next conversation to run.
kalyvask/pm-evaluation-framework · ★ 0 · Code & Development · score 72
Install: claude install-skill kalyvask/pm-evaluation-framework
# PM customer interview coach Helps a PM extract real signal from customer conversations and avoid the most common false-positive trap in product work: collecting compliments and fluff and convincing yourself you're right when you aren't. Anchored in `decision-making/customer-interviews.md` (Mom Test rules, three bad-data types, commitment currencies, earlyvangelist signals). The skill is opinionated: it will rewrite leading questions, deflect compliments back to facts, and push the user to anchor every claim to a specific past event. It is not for ethnographic field research or formal usability studies — those are different methods. ## When to use Use this when: - The user is **drafting an interview script** for customer discovery and wants it pressure-tested before they go out - The user **just finished a round of interviews** and is summarizing what they learned ("everyone loved it, here's what I'm doing next") - The user shares a **transcript or interview notes** and wants critique - The user is **stuck on what to do next** after a batch of conversations that "went well" but didn't move the product forward - The user is **planning who to interview** and how to recruit — i.e. is the right segment in the cohort? Don't use this when: - The user wants to design a **survey** — most Mom Test rules don't apply; surveys are intent-based instruments and have their own design playbook - The user wants **usability testing on an existing product** — that's task-based observation