interview-synthesis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Customer Interview Synthesis Expert

客户访谈综合分析专家

Overview

概述

Turn customer interview transcripts into actionable product opportunities. This skill takes raw question-and-answer transcripts and produces three artifacts: (1) themed insight clusters, (2) an opportunity solution tree mapping outcomes to opportunities and candidate solutions, and (3) a prioritized list of follow-up questions to close evidence gaps.

The synthesis approach is grounded in Teresa Torres' Continuous Discovery Habits (opportunity solution trees), Steve Portigal's interview methodology (looking for stories and contradictions), and the Jobs-To-Be-Done synthesis approach popularized by Alan Klement (situation-motivation-outcome decomposition).

将客户访谈记录转化为可执行的产品机会。本 skill 接收原始问答式访谈记录，并生成三项成果：（1）按主题组织的洞察聚类，（2）将结果与机会及候选解决方案建立映射的 Opportunity Solution Tree，（3）按优先级排列的后续问题列表，用于弥补证据缺口。

本综合分析方法以 Teresa Torres 的 Continuous Discovery Habits（Opportunity Solution Tree）、Steve Portigal 的访谈方法（寻找故事与矛盾），以及 Alan Klement 推广的 Jobs-To-Be-Done 综合分析方法（情境—动机—结果分解）为基础。

Core Capabilities

核心能力

Snippet extraction & coding — stories, contradictions, surprises, emotions coded by need/job/pain/gain and evidence strength
Theme clustering — evidence thresholds (>=3 snippets from >=2 participants) with scannable headlines
Opportunity solution tree — measurable outcome → customer-side opportunities → candidate solutions, with intact evidence trails
Follow-up generation — story-prompt questions targeting weak-evidence themes and unmapped assumptions
Multi-format output — markdown, JSON, mermaid, confluence, notion, linear

片段提取与编码——按 need/job/pain/gain 和证据强度对故事、矛盾、惊喜与情绪进行编码
主题聚类——设置证据阈值（>=3 个片段且来自 >=2 位参与者），并使用便于快速浏览的概括性标题
Opportunity Solution Tree——可衡量的结果 → 客户侧机会 → 候选解决方案，并保留完整的证据链
后续问题生成——针对证据薄弱的主题和未映射的假设生成故事提示问题
多格式输出——markdown、JSON、mermaid、confluence、notion、linear

When to Use

适用场景

Post-interview synthesis -- You have 3-20 interview transcripts and need to extract themes before they become stale.
Opportunity space mapping -- Building an opportunity solution tree before committing to solutions.
Discovery sprint readout -- Sharing findings with the product trio (PM, Design, Engineering) and stakeholders.
Evidence gap analysis -- Identifying which assumptions still lack interview evidence and need targeted follow-ups.

访谈后综合分析——你拥有 3–20 份访谈记录，需要在主题信息过时之前提取主题。
机会空间映射——在确定解决方案之前构建 Opportunity Solution Tree。
Discovery Sprint 成果汇报——与产品三人组（PM、Design、Engineering）及相关利益方分享研究发现。
证据缺口分析——识别哪些假设仍缺少访谈证据，需要有针对性地开展后续追问。

When NOT to Use

不适用场景

Quantitative survey synthesis -- use a data analysis skill instead.
Usability test debriefs -- use a UX research-specific workflow.
Sales call analysis for win/loss -- use
```
business-growth/
```
skills.

定量问卷综合分析——请改用数据分析 skill。
可用性测试复盘——请使用专门的 UX research 工作流。
用于赢单/丢单分析的销售电话分析——请使用
```
business-growth/
```
下的 skill。

Clarify First

先明确关键信息

Before synthesizing, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

The transcripts: how many (3-20) and their quality (synthesis is bounded by interview quality; thin input yields thin themes).
Target outcome: the measurable outcome that becomes the root of the opportunity solution tree.
Evidence threshold: what counts as a theme (default ≥3 snippets from ≥2 participants; raising/lowering it changes which clusters surface).
Output consumer: markdown / mermaid / Notion / Linear (sets the
```
--format
```
and shape of the deliverable).

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

开始综合分析前，请先明确以下输入。如果某项信息缺失或含糊，且会改变结果，应先询问；如果不会影响结果，则采用合理默认值并说明采用了哪一项默认值。

**访谈记录：**数量（3–20）及其质量（综合分析的效果受访谈质量限制；输入单薄，得出的主题也会单薄）。
**目标结果：**作为 Opportunity Solution Tree 根节点的可衡量结果。
**证据阈值：**什么条件可以构成一个主题（默认 ≥3 个片段且来自 ≥2 位参与者；提高或降低阈值会改变最终呈现的主题聚类）。
**输出使用者：**markdown / mermaid / Notion / Linear（用于决定
```
--format
```
和交付物形态）。

只需询问对本次请求最重要的两到三项输入，无需逐项确认整个列表。如果用户希望立即获得结果，请直接生成结果，并在开头说明你的假设。

Quick Start

快速开始

bash

python scripts/interview_synthesizer.py --input interviews.json --format markdown --output synthesis.md
python scripts/interview_synthesizer.py --input interviews.json --format mermaid   # tree only

Prepare input per

assets/interview_input_template.json

(one entry per interview: participant id, role, q/a pairs). See the references for the full framework and flag reference.

bash

python scripts/interview_synthesizer.py --input interviews.json --format markdown --output synthesis.md
python scripts/interview_synthesizer.py --input interviews.json --format mermaid   # tree only

请根据

assets/interview_input_template.json

准备输入（每场访谈一个条目：participant id、role、q/a pairs）。有关完整框架和 flag 参考说明，请参阅 references。

Anti-Patterns

反模式

Synthesis that confirms the starting hypothesis

只确认初始假设的综合分析

Mistake: Every theme matches what the PM believed before the interviews. Transcripts also mention pricing, trust or confusion, but none of it reaches the theme list. Why it happens: People pattern-match toward the answer they expect, and a solo pass has nothing to force a second reading. Instead: Require at least one finding that contradicts or expands the original hypothesis. Code surprises and contradictions as snippets, and have the product trio code independently before merging.

**错误：**每个主题都与 PM 在访谈前已有的判断一致。访谈记录中也提到了定价、信任或困惑，但这些内容都没有进入主题列表。 **发生原因：**人们会倾向于匹配自己预期的答案，而单次处理无法促使进行第二遍分析。 **正确做法：**至少要求得出一项与原始假设相矛盾或对其有所扩展的发现。将惊喜和矛盾编码为片段，并让产品三人组分别独立编码，然后再合并结果。

One theme pooled across segments

跨细分群体合并成一个主题

Mistake: A theme says "users want better onboarding" but draws on admins setting up the workspace and end users in week 1 as if they were one group. Why it happens: Each segment alone looks too thin to support a theme, so pooling feels like more evidence. Instead: Tag every theme with the segment it applies to. If two segments share a theme, apply the evidence threshold (3 or more snippets from 2 or more participants) to each segment separately.

**错误：**某个主题声称“用户需要更好的 onboarding”，但它将设置工作区的管理员和第一周的终端用户视为同一群体，并将两者的反馈混在一起。 **发生原因：**每个细分群体单独来看都不足以支撑一个主题，因此合并后反而显得证据更多。 **正确做法：**为每个主题标注其适用的细分群体。如果两个细分群体共享同一主题，则需要分别对每个群体应用证据阈值（3 个或更多片段，且来自 2 位或更多参与者）。

Percentages from a handful of interviews

根据少量访谈计算百分比

Mistake: "60% of users want feature X", when 3 of 5 interviewees mentioned it. Why it happens: A percentage looks more rigorous in a readout than a raw count. Instead: Write "X of N" for any sample under 20. Treat the theme as a candidate to survey or test quantitatively before anyone calls it a population-level finding.

Nine more, each with a bad and a good example:

references/red-flags.md

**错误：**声称“60% 的用户需要功能 X”，但实际上只有 5 位受访者中的 3 位提到了它。 **发生原因：**在汇报材料中，百分比看起来比原始计数更严谨。 **正确做法：**样本量少于 20 时，使用“N 位中有 X 位”的表述。在有人将其称为总体层面的结论之前，应先将该主题视为候选结论，并通过问卷或定量测试进行验证。

另外还有九项反模式，每项都包含错误与正确示例：

references/red-flags.md

。

References

参考资料

Load the reference that matches the task — keep this file lean and pull detail on demand:

references/synthesis-framework-and-tooling.md — the full 5-step framework (snippet extraction, coding, theme clustering, opportunity solution tree, follow-ups), end-to-end workflow, troubleshooting, success criteria, and the
```
interview_synthesizer.py
```
flag reference. Read when doing the synthesis or running the tool.
references/synthesis-methodology-guide.md — full methodology with worked examples bundling Torres, Portigal, and Klement. Read for the deeper "why" and end-to-end playbook.
references/red-flags.md — concrete bad-vs-good examples of how synthesis output goes wrong and how to fix it. Read before sharing themes, a tree, or a readout.
assets/interview_input_template.json — JSON schema for interview transcripts.
assets/opportunity_tree_template.md — editable opportunity solution tree template.

请加载与任务匹配的参考资料——让本文件保持精简，按需加载详细信息：

references/synthesis-framework-and-tooling.md——完整的 5 步框架（片段提取、编码、主题聚类、Opportunity Solution Tree、后续问题）、端到端工作流、故障排查、成功标准，以及
```
interview_synthesizer.py
```
的 flag 参考。执行综合分析或运行工具时阅读。
references/synthesis-methodology-guide.md——完整方法论及实战示例，涵盖 Torres、Portigal 和 Klement 的方法。需要深入理解背后的“为什么”以及端到端执行指南时阅读。
references/red-flags.md——综合分析输出出现问题的具体错误与正确示例，以及相应的修复方法。在分享主题、Opportunity Solution Tree 或汇报材料前阅读。
assets/interview_input_template.json——访谈记录的 JSON schema。
assets/opportunity_tree_template.md——可编辑的 Opportunity Solution Tree 模板。

Scope & Limitations

范围与限制

In Scope:

Qualitative synthesis of 3-20 customer interview transcripts
Theme clustering with evidence thresholds
Opportunity solution tree generation (Mermaid + Markdown)
Follow-up question generation for evidence gaps
Multi-format output (Markdown, JSON, Mermaid, Confluence, Notion, Linear)

Out of Scope:

Live interview facilitation -- this skill works on completed transcripts
Quantitative analysis (survey statistics, click-stream data)
Sentiment scoring via ML -- the tool uses deterministic keyword and code matching only
Win/loss analysis -- use
```
business-growth/
```
skills
Persona generation -- the output is opportunity-centric, not persona-centric

Important Caveats:

Synthesis quality is bounded by interview quality. Garbage in, garbage out.
The opportunity solution tree is a thinking aid, not a roadmap. Solutions still need experiment validation.
Teresa Torres' methodology assumes continuous discovery (weekly touchpoints). One-off interview rounds produce shallower trees.

范围内：

对 3–20 份客户访谈记录进行定性综合分析
按证据阈值进行主题聚类
生成 Opportunity Solution Tree（Mermaid + Markdown）
针对证据缺口生成后续问题
多格式输出（Markdown、JSON、Mermaid、Confluence、Notion、Linear）

范围外：

实时访谈主持——本 skill 仅处理已经完成的访谈记录
定量分析（问卷统计、点击流数据）
通过 ML 进行情感评分——该工具仅使用确定性关键词和代码匹配
赢单/丢单分析——请使用
```
business-growth/
```
下的 skill
Persona 生成——输出以机会为中心，而非以 Persona 为中心

重要注意事项：

综合分析的质量受访谈质量限制。垃圾进，垃圾出。
Opportunity Solution Tree 是一种思考辅助工具，而非路线图。解决方案仍需通过实验进行验证。
Teresa Torres 的方法论以持续发现为基础（每周开展接触点沟通）。一次性访谈轮次生成的 Opportunity Solution Tree 深度较浅。

Integration Points

集成点

Integration	Direction	What Flows
`discovery/brainstorm-experiments/`	Feeds into	Validated opportunities become hypotheses for lean experiments
`discovery/identify-assumptions/`	Bidirectional	Assumptions inform follow-up questions; interview evidence resolves assumptions
`discovery/brainstorm-ideas/`	Feeds into	Themed insights seed Product Trio ideation sessions
`discovery/pre-mortem/`	Feeds into	Pain themes surface candidate risks for pre-mortem analysis
`execution/create-prd/`	Feeds into	Top opportunities + supporting evidence populate PRD Background and Market Segments sections
`execution/job-stories/`	Feeds into	Klement-format job codes convert directly into When/Want/So job stories

集成项	方向	流转内容
`discovery/brainstorm-experiments/`	输入至	已验证的机会会成为精益实验的假设
`discovery/identify-assumptions/`	双向	假设用于形成后续问题；访谈证据用于澄清假设
`discovery/brainstorm-ideas/`	输入至	主题洞察为 Product Trio 创意研讨会提供灵感
`discovery/pre-mortem/`	输入至	痛点主题会暴露可供 pre-mortem 分析的候选风险
`execution/create-prd/`	输入至	首要机会及相关证据会填充 PRD 的 Background 和 Market Segments 部分
`execution/job-stories/`	输入至	Klement 格式的 job code 可直接转换为 When/Want/So 格式的 job story