product-lens
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseProduct Lens — Think Before You Build
产品视角——先思考再开发
This lane owns product diagnosis, not implementation-ready specification writing.
If the user needs a durable PRD-to-SRS or capability-contract artifact, hand off to .
product-capability该技能专注于产品诊断,而非撰写可直接用于实施的规范文档。
如果用户需要将PRD转化为SRS或生成能力契约类文档,请转交至。
product-capabilityWhen to Use
使用场景
- Before starting any feature — validate the "why"
- Weekly product review — are we building the right thing?
- When stuck choosing between features
- Before a launch — sanity check the user journey
- When converting a vague idea into a product brief before engineering planning starts
- 开始任何功能开发前——验证需求的“初衷”
- 每周产品评审——我们是否在做正确的事?
- 难以在多个功能间做选择时
- 产品发布前——对用户旅程进行合理性检查
- 在进入工程规划前,将模糊想法转化为产品简报时
How It Works
工作机制
Mode 1: Product Diagnostic
模式1:产品诊断
Like YC office hours but automated. Asks the hard questions:
1. Who is this for? (specific person, not "developers")
2. What's the pain? (quantify: how often, how bad, what do they do today?)
3. Why now? (what changed that makes this possible/necessary?)
4. What's the 10-star version? (if money/time were unlimited)
5. What's the MVP? (smallest thing that proves the thesis)
6. What's the anti-goal? (what are you explicitly NOT building?)
7. How do you know it's working? (metric, not vibes)Output: a with answers, risks, and a go/no-go recommendation.
PRODUCT-BRIEF.mdIf the result is "yes, build this," the next lane is , not more founder-theater.
product-capability类似YC办公时间的自动化版本,提出尖锐问题:
1. 这是面向谁的?(具体的人,而非“developers”这类泛称)
2. 用户的痛点是什么?(量化描述:发生频率、严重程度,用户当前的解决方式是什么?)
3. 为什么是现在?(哪些变化让这件事成为可能/必需?)
4. 理想的10分版本是什么样的?(假设时间和资金不受限制)
5. 最小可行产品(MVP)是什么?(能验证核心假设的最小功能集合)
6. 反目标是什么?(明确说明哪些内容不会去开发?)
7. 如何判断它有效?(用指标衡量,而非主观感受)输出:一份包含答案、风险以及是否推进建议的文档。
PRODUCT-BRIEF.md如果结果是“可以推进开发”,下一步应转交至,而非继续停留在创始人层面的讨论。
product-capabilityMode 2: Founder Review
模式2:创始人视角评审
Reviews your current project through a founder lens:
1. Read README, CLAUDE.md, package.json, recent commits
2. Infer: what is this trying to be?
3. Score: product-market fit signals (0-10)
- Usage growth trajectory
- Retention indicators (repeat contributors, return users)
- Revenue signals (pricing page, billing code, Stripe integration)
- Competitive moat (what's hard to copy?)
4. Identify: the one thing that would 10x this
5. Flag: things you're building that don't matter通过创始人的视角评审当前项目:
1. 阅读README、CLAUDE.md、package.json以及近期提交记录
2. 推断:该项目的定位是什么?
3. 评分:产品市场契合度指标(0-10分)
- 使用量增长趋势
- 留存指标(重复贡献者、回头用户)
- 营收信号(定价页面、计费代码、Stripe集成)
- 竞争壁垒(哪些内容难以被复制?)
4. 识别:能让项目价值提升10倍的核心举措
5. 标记:正在开发但无关紧要的内容Mode 3: User Journey Audit
模式3:用户旅程审计
Maps the actual user experience:
1. Clone/install the product as a new user
2. Document every friction point (confusing steps, errors, missing docs)
3. Time each step
4. Compare to competitor onboarding
5. Score: time-to-value (how long until the user gets their first win?)
6. Recommend: top 3 fixes for onboarding映射真实的用户体验:
1. 以新用户身份克隆/安装产品
2. 记录每个摩擦点(步骤混淆、错误、文档缺失)
3. 统计每个步骤的耗时
4. 与竞品的入门流程进行对比
5. 评分:价值交付时长(用户获得首次正向反馈所需的时间)
6. 建议:入门流程的三大优化方案Mode 4: Feature Prioritization
模式4:功能优先级排序
When you have 10 ideas and need to pick 2:
1. List all candidate features
2. Score each on: impact (1-5) × confidence (1-5) ÷ effort (1-5)
3. Rank by ICE score
4. Apply constraints: runway, team size, dependencies
5. Output: prioritized roadmap with rationale当有10个想法需要选出2个时:
1. 列出所有候选功能
2. 按以下公式评分:影响力(1-5分)× 置信度(1-5分)÷ 投入成本(1-5分)
3. 按ICE分数排序
4. 应用约束条件:资金储备、团队规模、依赖关系
5. 输出:带有决策依据的优先级 roadmapOutput
输出结果
All modes output actionable docs, not essays. Every recommendation has a specific next step.
所有模式都会输出可落地的文档,而非空泛的论述。每一条建议都包含明确的下一步行动。
Integration
集成搭配
Pair with:
- to verify the user journey audit findings
/browser-qa - for visual polish assessment
/design-system audit - for post-launch monitoring
/canary-watch - when the product brief needs to become an implementation-ready capability plan
product-capability
搭配使用:
- :验证用户旅程审计的发现
/browser-qa - :评估视觉优化程度
/design-system audit - :发布后监控
/canary-watch - :当产品简报需要转化为可实施的能力规划时
product-capability