菜单
Plan, conduct, or analyze non-leading customer interviews that produce behavioral evidence. Use when the user needs an interview guide, wants to evaluate interview notes, must distinguish signal from compliments or hypothetical intent, or needs a recruiting and synthesis plan.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Route product-management work to the smallest relevant set of operational PM skills. Use when the user invokes /pm, asks a broad or ambiguous product question, needs help choosing a PM method, or requests discovery, strategy, positioning, pricing, metrics, experiments, prioritization, roadmaps, requirements, launch, stakeholder, AI-product, or product-review work.
Design an AI-product evaluation system connecting task quality, user outcomes, failure taxonomies, datasets, human judgment, automated checks, release thresholds, and production monitoring. Use when defining AI quality, comparing models or prompts, deciding launch readiness, or diagnosing regressions.
Decide whether a product problem should use AI and define the appropriate human-AI workflow. Use when a team starts with a model or agent idea, must compare AI with deterministic software or process change, needs an AI use-case brief, or must assess data, uncertainty, value, feasibility, cost, and fallback fit.
Review AI-product safety, reliability, privacy, security, fairness, uncertainty, human oversight, fallback, monitoring, drift, latency, and cost risks. Use for AI launch gates, agent actions, high-impact automation, incident preparation, production failure analysis, or system feasibility review.
Discover and validate product opportunities before committing to delivery. Use when a team has feature requests but weak problem evidence, needs to identify customer opportunities, must reduce value or usability risk, or wants a continuous discovery plan tied to an outcome.
Design the smallest reliable experiment or assumption test capable of changing a product decision. Use when the user has a hypothesis, wants an A/B test or prototype test, needs causal evidence, must choose an evidence standard, or wants success, guardrail, stop, and interpretation rules.
| name | product-interview |
| description | Plan, conduct, or analyze non-leading customer interviews that produce behavioral evidence. Use when the user needs an interview guide, wants to evaluate interview notes, must distinguish signal from compliments or hypothetical intent, or needs a recruiting and synthesis plan. |
Collect specific evidence about a customer's recent behavior, constraints, alternatives, and commitments without pitching for approval.
Define:
Classify each note as:
Use the first four as stronger evidence. Preserve the rest as context, not validation.
Return the interview objective, screener, guide, prohibited leading questions, note schema, evidence summary, contradictions, confidence, and next decision.
Operational synthesis informed by The Mom Test and the interview and story-mapping practices in Continuous Discovery Habits.
