Design sprint

Skill bg-szy/TOP-SKILLS/skills/superskills/design-sprint

全球最大的 Claude Code 技能聚合库 · 收录 3900+ 来自 12+ 来源的技能，提供在线搜索与趋势分析看板 / The world's largest Claude Code skill aggregation hub — 3900+ skills from 12+ sources with online search and trend dashboard

Install

npx -y skills add bg-szy/TOP-SKILLS --skill design-sprint

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate in a week", "rapid prototype", "test with users", "de-risk before building", "GV sprint", "prototype testing", or "design workshop". Also trigger when a team needs to make a critical product decision quickly, resolve stakeholder disagreements, or test risky ideas before investing in development. Covers mapping, sketching, deciding, prototyping, and testing. For ongoing experimentation, see lean-startup. For customer job analysis, see jobs-to-be-done.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.7 KB, as published. Nobody here has run it

Design Sprint Framework

Core Framework

The Design Sprint compresses product development cycles into five days: Map (Monday), Sketch (Tuesday), Decide (Wednesday), Prototype (Thursday), and Test (Friday).

Prerequisites:

Important problem worth dedicated focus
Decision maker + 4-7 diverse team members
Full 5 days (10am-5pm, uninterrupted)
Dedicated workspace with whiteboards

Scoring: Rate 0-10 based on adherence to structure, time-boxing, prototyping, and user testing.

Daily Breakdown

Monday: Map

Define 2-year goal and sprint questions
Map customer journey (5-15 steps)
Interview experts, capture "How Might We" opportunities
Select target customer moment for focus

Tuesday: Sketch

Lightning demos for inspiration
Individual solution sketches (no group brainstorming)
Four-step process: Notes → Ideas → Crazy 8s → Solution Sketch
Anonymous 3-panel storyboards showing user experience

Wednesday: Decide

Gallery critique with silent dot voting
Decider uses supervote (3 dots override)
Create 10-15 panel storyboard for prototype
Combine best ideas into unified solution

Thursday: Prototype

Assign roles: Makers, Stitcher, Writer, Collector, Interviewer
Build realistic facade (not working code)
Tools: Figma, Keynote, or prototyping platforms
Trial run before Friday testing

Friday: Test

Conduct 5 customer interviews (30 minutes each)
Five-act structure: Welcome → Context → Introduce → Tasks → Debrief
Team observes, records patterns
Identify what worked, what failed, next steps

Key Principles

Five customers reveal patterns after 3-5 interviews; diminishing returns after 5
Prototype fidelity: Facade quality—realistic enough for honest reactions, not production-ready
No explaining: Let users interpret and struggle; observe confusion
Decider authority: Final call on Tuesday solutions and Wednesday decision
Time protection: No interruptions; full commitment required

Common Mistakes to Avoid

Error	Solution
Skip prototyping	Always build, even simply
Over-engineer prototype	Focus on facade only
Test wrong users	Screen for target customers
Explain to users	Let them struggle independently
No decision maker	Commitment required or postpone
Interruptions	Protect focus entirely

Variations

4-Day Sprint: Compress Map + Sketch into Day 1
Remote Sprint: Use Miro/FigJam, Zoom, same structure
Multi-Sprint: Sequential sprints on broad → detailed → refined problems

Diagnostic Checklist

Confirm before sprinting:

Decider committed for full week
Problem important enough
Prototype feasible in 1 day
Can recruit 5 target users
Team protected from interruptions

Source: Framework developed at Google Ventures by Jake Knapp; detailed in "Sprint: How to Solve Big Problems and Test New Ideas in Just Five Days" by Knapp, Zeratsky, and Kowitz.