feedback-synthesis
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseFeedback Synthesis
反馈综合分析
When to Use
何时使用
Activate when a founder or product lead needs to make sense of customer feedback from multiple sources -- support tickets, NPS surveys, user interviews, app store reviews, social media, sales call notes, feature request logs, spreadsheets, or CSVs. This includes prompts like "analyze our customer feedback," "what are users asking for most," "prioritize feature requests," "triage this backlog," or "what themes are showing up in our support tickets."
当创始人或产品负责人需要梳理来自多个来源的客户反馈时，启用此技能——支持工单、NPS 调查、用户访谈、应用商店评论、社交媒体、销售通话记录、功能请求日志、电子表格或 CSV。适用于“分析我们的客户反馈”“用户最常提出哪些需求”“确定功能请求的优先级”“梳理待办事项”“支持工单中出现了哪些主题”等提示。
Context Required
所需上下文
- From startup-context: product type, customer segments, current product roadmap priorities, company stage, strategic goals, and product objectives.
- From the user: the raw feedback data (or access to it), the sources being analyzed, the time period, the product goal or desired outcomes guiding prioritization, and the decision this analysis will inform.
- **From startup-context：**产品类型、客户细分、当前产品路线图优先级、公司阶段、战略目标以及产品目标。
- **From user：**原始反馈数据（或访问权限）、所分析的来源、时间范围、用于指导优先级排序的产品目标或预期结果，以及本次分析将支持什么决策。
Workflow
工作流
- Understand the goal -- Confirm the product objective and desired outcomes that will guide prioritization. Feedback analysis without a strategic lens produces noise, not signal.
- Collect and normalize -- Gather feedback from all sources. If data is in structured formats (CSV, spreadsheet), create summary tables. Each piece of feedback becomes a row with source, date, customer segment, verbatim quote, and sentiment.
- Categorize into themes -- Group related requests and feedback together. Name each theme. Focus on identifying the underlying opportunity (problem) rather than the surface-level feature request.
- Assess strategic alignment -- For each theme, evaluate how well it aligns with the stated product goals and company strategy.
- Score with Opportunity Score -- Use the Opportunity Score framework (Dan Olsen): Opportunity Score = Importance x (1 - Satisfaction), normalized to 0-1. This prioritizes problems that matter most and are least well-served today.
- Prioritize top opportunities -- Select the top 3 themes based on impact (customer value and breadth of users affected), effort (development and design resources required), risk (technical and market uncertainty), and strategic alignment (fit with product vision).
- Deep-dive top items -- For each top opportunity, document: rationale, alternative solutions worth considering, high-risk assumptions, and how to test those assumptions with minimal effort.
- Present findings -- Deliver a structured synthesis with executive summary first, supporting data second, and recommended actions third.
- 理解目标——确认用于指导优先级排序的产品目标和预期结果。没有战略视角的反馈分析只会产生噪声，而非有效信号。
- 收集并标准化——收集所有来源的反馈。如果数据采用结构化格式（CSV、电子表格），则创建汇总表。每条反馈都成为一行，包含来源、日期、客户细分、原话引述和情感倾向。
- 归类为主题——将相关请求和反馈归为一组。为每个主题命名。重点识别潜在机会（问题），而不是表面上的功能请求。
- 评估战略契合度——针对每个主题，评估其与既定产品目标和公司战略的契合程度。
- 使用 Opportunity Score 评分——使用 Opportunity Score 框架（Dan Olsen）：Opportunity Score = Importance x (1 - Satisfaction)，并归一化至 0-1。这可以优先识别最重要且当前最得不到满足的问题。
- 确定首要机会——基于影响力（客户价值和受影响用户范围）、投入（所需的开发与设计资源）、风险（技术和市场不确定性）以及战略契合度（与产品愿景的匹配程度），选出前 3 个主题。
- 深入分析重点事项——针对每个首要机会，记录：理由、值得考虑的替代解决方案、高风险假设，以及如何以最低成本验证这些假设。
- 呈现发现——交付结构化的综合分析报告，依次包含执行摘要、支撑数据和推荐行动。
Output Format
输出格式
Synthesis Report Template
综合分析报告模板
undefinedundefinedCustomer Feedback Synthesis -- [Period]
Customer Feedback Synthesis -- [Period]
Executive Summary
Executive Summary
3-5 key findings. Lead with the most surprising or actionable insight.
3-5 key findings. Lead with the most surprising or actionable insight.
Product Goal Alignment
Product Goal Alignment
The stated product objective and how feedback themes map to it.
The stated product objective and how feedback themes map to it.
Theme Map
Theme Map
| Theme | Frequency | Segments Affected | Opportunity Score | Strategic Alignment | Priority |
|---|---|---|---|---|---|
| [Theme] | [Count] | [Segments] | [Score] | [High/Med/Low] | [H/M/L] |
| Theme | Frequency | Segments Affected | Opportunity Score | Strategic Alignment | Priority |
|---|---|---|---|---|---|
| [Theme] | [Count] | [Segments] | [Score] | [High/Med/Low] | [H/M/L] |
Top 3 Opportunities (Deep Dives)
Top 3 Opportunities (Deep Dives)
Opportunity 1: [Theme Name]
Opportunity 1: [Theme Name]
- Rationale: Customer needs and strategic alignment
- Representative quotes: Direct user language
- Alternative solutions: Other ways to address this need
- High-risk assumptions: What must be true
- Cheapest test: How to validate with minimal effort
- Rationale: Customer needs and strategic alignment
- Representative quotes: Direct user language
- Alternative solutions: Other ways to address this need
- High-risk assumptions: What must be true
- Cheapest test: How to validate with minimal effort
Quick Wins
Quick Wins
Actions that address frequent feedback with low implementation effort.
Actions that address frequent feedback with low implementation effort.
Not Prioritized (and Why)
Not Prioritized (and Why)
Themes explicitly deprioritized with reasoning.
Themes explicitly deprioritized with reasoning.
Appendix: Raw Data Summary
Appendix: Raw Data Summary
Breakdown by source, segment, and time period.
undefinedBreakdown by source, segment, and time period.
undefinedFrameworks & Best Practices
框架与最佳实践
Opportunities Over Features
机会优先于功能（Opportunities Over Features）
Never let customers design solutions. Prioritize opportunities (problems), not features. When a user says "I want a Gantt chart," the underlying opportunity might be "I need to visualize project timelines and communicate status to stakeholders." Always dig for the job-to-be-done behind the request.
绝不能让客户来设计方案。应优先考虑机会（问题），而不是功能。当用户说“我想要一个 Gantt chart”时，潜在机会可能是“我需要可视化项目时间线并向利益相关者沟通状态”。始终深入挖掘请求背后的 job-to-be-done。
Opportunity Score (Dan Olsen)
Opportunity Score（Dan Olsen）
Score each theme: Opportunity Score = Importance x (1 - Satisfaction), normalized to 0-1. This surfaces problems that are both important and underserved. A high-importance, high-satisfaction area is already well-served and should not be prioritized over a high-importance, low-satisfaction gap.
为每个主题评分：Opportunity Score = Importance x (1 - Satisfaction)，并归一化至 0-1。这能识别出既重要又未得到充分满足的问题。重要性高且满意度也高的领域已经得到了良好服务，不应优先于重要性高但满意度低的需求缺口。
Signal vs. Noise Rules
Signal vs. Noise 规则
- One customer saying it is not a pattern. Require 3+ independent mentions of a theme before treating it as a signal. Exception: if the one customer is a whale account citing it as a churn risk.
- Recency bias check. A flood of recent feedback about one issue can overshadow a persistent problem. Always compare against the prior period.
- Loudest does not equal most important. Power users and vocal customers generate disproportionate feedback. Weight by segment size and revenue contribution, not volume alone.
- Praise is data too. Track what users love. Knowing your strengths prevents you from accidentally breaking them during a redesign.
- 一个客户提出并不构成模式。 某个主题至少出现 3 次以上独立提及后，才应将其视为信号。例外情况：如果提出该问题的是一个大客户账户（whale account），并将其列为流失风险。
- 检查近期偏差。 近期大量涌现的关于某一个问题的反馈，可能掩盖一个长期存在的问题。始终与上一周期进行比较。
- 声音最大不等于最重要。 Power users（重度用户）和发声活跃的客户会贡献不成比例的反馈。应根据客户细分规模和收入贡献进行加权，而不是只看反馈数量。
- 表扬也是数据。 了解用户喜爱什么，可以避免在重新设计时无意破坏这些优势。
Assumption Testing
假设测试（Assumption Testing）
For each top-priority opportunity, identify the highest-risk assumption and design the cheapest possible test. Do not build the full solution to validate an assumption that could be tested with a prototype, survey, or Wizard of Oz experiment.
针对每个高优先级机会，识别风险最高的假设，并设计成本最低的可行测试。不要为了验证一个可以通过原型、问卷或 Wizard of Oz 实验验证的假设，而直接构建完整解决方案。
Source-Specific Guidance
按来源划分的指导建议
| Source | Strengths | Watch Out For |
|---|---|---|
| Support tickets | High signal, specific problems | Skews toward bugs, misses satisfied users |
| NPS/surveys | Broad coverage, quantifiable | Low response rates can bias results |
| Feature request boards | Organized, vote counts available | Power users dominate voting |
| Sales call notes | Revenue-adjacent, prospect perspective | Prospects request features they may never use |
| App store reviews | Public, includes competitor comparisons | Skews negative, vague complaints |
| Social media | Unfiltered, real-time | Noisy, hard to segment |
| 来源 | 优势 | 注意事项 |
|---|---|---|
| 支持工单 | 信号强、问题具体 | 偏向 Bug，遗漏满意用户 |
| NPS/调查 | 覆盖范围广、可量化 | 回复率低可能导致偏差 |
| 功能请求看板 | 组织有序、可获取投票数 | Power users 在投票中占主导 |
| 销售通话记录 | 与收入相关、潜在客户视角 | 潜在客户请求的功能可能永远不会使用 |
| 应用商店评论 | 公开、包含竞品对比 | 偏负面、抱怨含糊 |
| 社交媒体 | 未经筛选、实时 | 噪声大、难以细分 |
Avoiding Common Mistakes
避免常见错误
- Cherry-picking quotes that support a pre-existing hypothesis. Present the full distribution, including contradictory feedback.
- Conflating frequency with importance. A low-frequency issue that causes churn matters more than a high-frequency annoyance users tolerate.
- Delivering data without recommendations. A theme map without action items is a report, not a synthesis. Always end with what to do next.
- Ignoring the silent majority. Users who never complain may be happy or disengaged. Segment analysis helps distinguish the two.
- 挑选支持既有假设的引述。 应呈现完整的数据分布，包括相互矛盾的反馈。
- 混淆频率与重要性。 一个低频但会导致流失的问题，比一个用户能够容忍的高频小问题更重要。
- 只交付数据而不给出建议。 没有行动项的主题图谱只是报告，而不是综合分析。始终以“接下来要做什么”结束。
- 忽视沉默的大多数。 从不抱怨的用户可能感到满意，也可能已经失去兴趣。细分分析有助于区分这两种情况。
Related Skills
相关 Skills
- -- Chain when feedback analysis reveals gaps that need dedicated user research (interviews, usability tests).
user-research-synthesis - -- Chain when feedback themes correlate with churn patterns and need deeper retention analysis.
churn-analysis - -- Chain when a clear opportunity emerges from the synthesis and needs to be specced into a PRD.
prd-writing
- ——当反馈分析暴露出需要专门用户研究（访谈、可用性测试）的缺口时，链式调用。
user-research-synthesis - ——当反馈主题与流失模式相关，需要进行更深入的留存分析时，链式调用。
churn-analysis - ——当综合分析发现了明确的机会，需要将其编写成 PRD 时，链式调用。
prd-writing
Examples
示例
Example 1: Feature request prioritization
示例 1：功能请求优先级排序
User: "Our feature request board has 150 items. Help me figure out what to build next quarter."
Good output excerpt:
Executive Summary: 150 requests cluster into 9 themes. The top opportunity is not the most-requested feature (SSO, 34 votes) but the most underserved need: "real-time collaboration on shared documents" (Opportunity Score: 0.82). SSO scores lower (0.45) because existing workarounds satisfy most users adequately.Opportunity 1: Real-time collaboration
- Rationale: 22 requests across 4 segments. Cited as expansion blocker in 3 enterprise deals worth $85K ARR. Current satisfaction: 2/10.
- Alternative solutions: (a) Full real-time editing, (b) Lightweight commenting and presence indicators, (c) Async review workflow with notifications
- High-risk assumption: Users want simultaneous editing, not just awareness of others' changes
- Cheapest test: Add presence indicators only (show who is viewing a document) and measure whether collaboration-related tickets decrease
用户：“我们的功能请求看板有 150 个条目。帮我们确定下个季度要构建什么。”
优秀输出节选：
**执行摘要：**150 个请求可归为 9 个主题。首要机会并非请求最多的功能（SSO，34 票），而是尚未被充分满足的最大需求：“共享文档的实时协作”（Opportunity Score：0.82）。SSO 得分较低（0.45），因为现有替代方案已能较好地满足大多数用户。机会 1：实时协作
- **理由：**跨 4 个客户细分的 22 个请求。在 3 个价值 85K ARR 的企业交易中，被视为扩张阻碍因素。当前满意度：2/10。
- 替代解决方案：（a）完整的实时编辑功能；（b）轻量级评论和在线状态指示器；（c）带通知的异步审查工作流。
- **高风险假设：**用户需要的是同时编辑，而不只是感知到其他人的修改。
- **最低成本测试：**仅添加在线状态指示器（显示谁正在查看文档），并衡量与协作相关的工单是否减少。
Example 2: Multi-source synthesis
示例 2：多来源综合分析
User: "We have 200 support tickets, 50 NPS responses, and notes from 10 customer interviews from last month. What are customers telling us?"
Good output excerpt:
Theme 1: CSV export broken for large datasets (Opportunity Score: 0.91)
- 47 support tickets, 8 NPS detractors, 3 interviews. Users hitting the 10K row limit work around it by splitting exports manually.
- Strategic alignment: High -- data export is core to our "open platform" positioning.
- Cheapest test: Not needed; this is a clear bug/limitation. Fix directly.
- Quick win: Increase CSV export limit to 100K rows (engineering estimate: 2 days).
用户：“我们有上个月的 200 个支持工单、50 份 NPS 回复，以及 10 次客户访谈的记录。客户在告诉我们什么？”
优秀输出节选：
主题 1：大型数据集的 CSV 导出失败（Opportunity Score：0.91）
- 47 个支持工单、8 个 NPS 贬损者、3 次访谈。遇到 10K 行限制的用户只能手动拆分导出作为变通方案。
- **战略契合度：**高——数据导出是我们“开放平台”定位的核心能力。
- **最低成本测试：**不需要；这是一个明确的 Bug/限制。直接修复即可。
- **快速见效项：**将 CSV 导出上限提高到 100K 行（工程估算：2 天）。