design-sprint by wondelai/skills
npx skills add https://github.com/wondelai/skills --skill design-sprint一个为期五天的流程,通过设计、原型制作和与客户测试想法来回答关键业务问题。由 Google Ventures 开发,并被 Google、Slack、Airbnb 及数百家初创公司使用。
优秀的解决方案需要深度工作和快速迭代。 设计冲刺将数月的辩论、设计和测试压缩到一周内,创造出专注和紧迫感,从而消除无休止的讨论。
基础: 传统的产品开发浪费数月时间构建错误的东西。设计冲刺通过在编写生产代码之前与真实用户进行测试,来降低产品决策的风险。
目标:10/10。 在规划或执行设计冲刺时,根据对以下原则的遵守程度,以 0-10 分进行评分。10/10 意味着结构合理、时间盒控制、原型制作和用户测试;较低的分数表示跳过了步骤或测试不足。始终提供当前分数以及达到 10/10 所需的具体改进措施。
周一 → 周二 → 周三 → 周四 → 周五
地图 草图 决策 原型 测试
先决条件:
冲刺导师: 一人负责引导、计时、管理团队精力。
目标: 理解问题并选择本周的目标。
练习:长期目标
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
练习:冲刺问题
格式: 写在白板上,整个团队参与贡献
练习:绘制客户旅程地图
练习:请教专家
练习:"我们如何能" 笔记
练习:选择目标
决策者: 拥有最终决定权的人。
周一产出:
参见:references/monday.md 获取周一的详细练习和引导说明。
目标: 生成解决方案。每个人绘制一个详细的解决方案草图。
练习:寻找灵感
练习:分工或集中
目标: 每个人独立绘制一个详细的解决方案草图(不是小组合作!)
步骤 1:笔记(20 分钟)
步骤 2:想法(20 分钟)
步骤 3:疯狂八分钟(8 分钟)
步骤 4:解决方案草图(30-90 分钟)
关键点: 不要进行小组头脑风暴。独立工作能产生更好、更多样化的想法。
周二产出:
参见:references/tuesday.md 获取草图模板和示例。
目标: 评审解决方案并选择最佳方案进行原型制作和测试。
练习:艺术博物馆
练习:热图评审
练习:非正式投票
决策者: 拥有决策权的人获得三个大圆点(超级投票权)。他们的决定胜出。
如果有多个获胜方案:
大多数冲刺: 合而为一(原型制作和测试更简单)
练习:故事板
故事板规则:
周三产出:
参见:references/wednesday.md 获取决策练习和故事板模板。
目标: 构建一个逼真的外观。你需要一些东西在周五进行测试。
原型心态:
原型保真度:
制作者(2 人以上):
整合者(1 人):
文案(1 人):
收集者(1-2 人):
访谈者(1 人):
冲刺导师:
工具:
周四上午:
周四下午:
原型检查清单:
周四产出:
参见:references/thursday.md 获取原型制作工具和技术。
目标: 访谈 5 位客户,了解哪些有效,哪些无效。
访谈室:
观察室:
角色:
第一幕:友好欢迎(5 分钟)
第二幕:背景问题(5 分钟)
第三幕:介绍原型(5 分钟)
第四幕:任务和提示(15 分钟)
第五幕:总结(5 分钟)
访谈时长: 每位客户约 30 分钟
访谈之间:
为什么是 5 位客户?
招募对象:
观看访谈时,团队记录:
| 列 1 | 列 2 | 列 3 | 列 4 | 列 5 |
|---|---|---|---|---|
| 客户 1 笔记 | 客户 2 笔记 | 客户 3 笔记 | 客户 4 笔记 | 客户 5 笔记 |
用 ✓、✗ 或 ~ 标记:
完成全部 5 次访谈后:
整理发现:
✓ 有效的部分:
✗ 失败的部分:
~ 混合结果:
后续步骤:
周五产出:
参见:references/friday.md 获取访谈脚本和笔记模板。
在以下情况下进行冲刺:
不要在以下情况下进行冲刺:
4 天冲刺:
远程冲刺:
多轮冲刺:
| 错误 | 失败原因 | 解决方案 |
|---|---|---|
| 跳过原型制作 | 没有东西可测试 | 始终制作原型,即使很简单 |
| 过度设计原型 | 在无关紧要的细节上浪费时间 | 仅外观,非可运行代码 |
| 用错用户测试 | 反馈无效 | 筛选目标客户 |
| 向用户解释原型 | 破坏了测试目的 | 让他们挣扎,观察困惑点 |
| 没有决策者 | 无法做出决策承诺 | 确保决策者参与整周,否则不要进行冲刺 |
| 干扰 | 破坏专注力 | 保护这一周,不开会/不处理邮件 |
审核任何冲刺计划:
| 问题 | 如果答案为否 | 行动 |
|---|---|---|
| 我们有决策者参与整周吗? | 冲刺会失败 | 获得承诺或推迟 |
| 问题足够重要吗? | 浪费时间 | 只对重大挑战进行冲刺 |
| 我们能在 1 天内制作原型吗? | 不适合冲刺的问题 | 选择更具体的问题 |
| 我们能招募到 5 位目标用户吗? | 无法正确测试 | 立即开始招募(提前 2 周) |
| 团队能承诺不受干扰吗? | 无法保持专注 | 获得领导层的支持 |
此技能基于 Google Ventures 开发的设计冲刺流程。关于完整的方法论、练习和案例研究:
Jake Knapp 在 Google 期间创建了设计冲刺流程,他在 Gmail、Chrome 和 Google X 等产品上运行过冲刺。作为 Google Ventures(现 GV)的设计合伙人,他通过为 GV 投资组合中的初创公司运行了 100 多次冲刺来完善该流程。设计冲刺现已被 Google、Slack、Airbnb、LEGO 及全球数千家公司使用。Jake 还是《Make Time》的作者,该书是关于专注和精力的框架。
每周安装量
278
代码库
GitHub 星标数
272
首次出现
2026年2月10日
安全审计
安装于
opencode257
codex254
gemini-cli252
cursor249
github-copilot249
kimi-cli247
A five-day process for answering critical business questions through design, prototyping, and testing ideas with customers. Developed at Google Ventures and used by Google, Slack, Airbnb, and hundreds of startups.
Great solutions require both deep work and fast iteration. The Design Sprint compresses months of debate, design, and testing into a single week, creating focus and urgency that eliminates endless discussion.
The foundation: Traditional product development wastes months building the wrong thing. Design Sprints de-risk product decisions by testing with real users before writing production code.
Goal: 10/10. When planning or executing a Design Sprint, rate it 0-10 based on adherence to the principles below. A 10/10 means proper structure, time-boxing, prototyping, and user testing; lower scores indicate skipping steps or insufficient testing. Always provide the current score and specific improvements needed to reach 10/10.
Monday → Tuesday → Wednesday → Thursday → Friday
Map Sketch Decide Prototype Test
Prerequisites:
Sprint Master: One person facilitates, keeps time, manages energy.
Goal: Understand the problem and choose a target for the week.
Exercise: Long-term goal
Exercise: Sprint questions
Format: Write on whiteboard, entire team contributes
Exercise: Map the customer journey
Exercise: Ask the Experts
Exercise: How Might We (HMW) notes
Exercise: Choose the target
Decider: The person with authority makes the final call.
Monday output:
See: references/monday.md for detailed Monday exercises and facilitation.
Goal: Generate solutions. Each person sketches a detailed solution.
Exercise: Find inspiration
Exercise: Divide or swarm
Goal: Everyone individually sketches a detailed solution (not as a group!)
Step 1: Notes (20 minutes)
Step 2: Ideas (20 minutes)
Step 3: Crazy 8s (8 minutes)
Step 4: Solution Sketch (30-90 minutes)
Critical: No group brainstorming. Individual work produces better, more diverse ideas.
Tuesday output:
See: references/tuesday.md for sketching templates and examples.
Goal: Critique solutions and choose the best one to prototype and test.
Exercise: Art museum
Exercise: Heat map review
Exercise: Straw poll
Decider: Person with authority gets three large dots (supervote). Their decision wins.
If multiple winners:
Most sprints: All-in-one (simpler to prototype and test)
Exercise: Storyboard
Storyboard rules:
Wednesday output:
See: references/wednesday.md for decision exercises and storyboard templates.
Goal: Build a realistic facade. You need something to test on Friday.
Prototype mindset:
Prototype fidelity:
Makers (2+ people):
Stitcher (1 person):
Writer (1 person):
Collector (1-2 people):
Interviewer (1 person):
Sprint Master:
Tools:
Thursday morning:
Thursday afternoon:
Prototype checklist:
Thursday output:
See: references/thursday.md for prototyping tools and techniques.
Goal: Interview 5 customers, learn what works and what doesn't.
Interview room:
Observation room:
Roles:
Act 1: Friendly Welcome (5 min)
Act 2: Context Questions (5 min)
Act 3: Introduce the Prototype (5 min)
Act 4: Tasks and Nudges (15 min)
Act 5: Debrief (5 min)
Interview length: ~30 minutes per customer
Between interviews:
Why 5 customers?
Who to recruit:
While watching interviews, team captures:
| Column 1 | Column 2 | Column 3 | Column 4 | Column 5 |
|---|---|---|---|---|
| Customer 1 notes | Customer 2 notes | Customer 3 notes | Customer 4 notes | Customer 5 notes |
Mark with ✓, ✗, or ~:
After all 5 interviews:
Organize findings:
✓ What worked:
✗ What failed:
~ Mixed results:
Next steps:
Friday output:
See: references/friday.md for interview scripts and note-taking templates.
Run a sprint when:
Don't run a sprint when:
4-Day Sprint:
Remote Sprint:
Multi-Sprint:
| Mistake | Why It Fails | Fix |
|---|---|---|
| Skip prototyping | Nothing to test | Always prototype, even if simple |
| Over-engineer prototype | Waste time on details that don't matter | Facade only, not working code |
| Test with wrong users | Invalid feedback | Screen for target customers |
| Explain prototype to users | Defeats the test | Let them struggle, observe confusion |
| No decision maker | Can't commit to decision | Get Decider for full week or don't sprint |
| Interruptions | Breaks focus | Protect the week, no meetings/emails |
Audit any sprint plan:
| Question | If No | Action |
|---|---|---|
| Do we have a Decider for full week? | Sprint will fail | Get commitment or postpone |
| Is the problem important enough? | Waste of time | Only sprint on big challenges |
| Can we prototype in 1 day? | Wrong problem for sprint | Choose more concrete problem |
| Can we recruit 5 target users? | Can't test properly | Start recruiting now (2 weeks ahead) |
| Will team commit to no interruptions? | Won't maintain focus | Get buy-in from leadership |
This skill is based on the Design Sprint process developed at Google Ventures. For the complete methodology, exercises, and case studies:
Jake Knapp created the Design Sprint process while at Google, where he ran sprints on products like Gmail, Chrome, and Google X. As a design partner at Google Ventures (now GV), he refined the process by running over 100 sprints with startups in the GV portfolio. The Design Sprint is now used by teams at Google, Slack, Airbnb, LEGO, and thousands of companies worldwide. Jake is also the author of Make Time , a framework for focus and energy.
Weekly Installs
278
Repository
GitHub Stars
272
First Seen
Feb 10, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode257
codex254
gemini-cli252
cursor249
github-copilot249
kimi-cli247
推荐与联盟计划设计优化指南:病毒式增长营销策略、客户推荐计划、联盟营销
26,100 周安装