Apply Design Thinking's five stages — Empathize, Define, Ideate, Prototype, Test — to solve user-centered problems.
SkillScore83Maintained
Automatic
◆Design & UX Review pack
Last verified 8/28/2026
What it changes
Passed 19 of 23 test cases with the skill, and 10 of 23 without it.
Without skill43%
With skill83%
Checks it passed that the model alone missed
The Prototype section specifies the assumption under test.
The Test section explicitly lists invalidated assumptions from user testing.
Clickable digital mocks are designated to test interactive tap accuracy on screen.
and 9 more in the full report
9 fixed10 passed either way4 still failing0 broke
Pass-rate lift
+39 pp
Tokens
+5%
Agent turns
0%
Response time
-37%
Model gemini-3.6-flashMeasured 8/28/2026v119 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
A product team has three different questions to answer for a smart watch fitness application: 1) Is the high-level step-goal navigation flow intuitive? 2) Can users accurately tap tiny heart-rate buttons on a small screen? 3) Can local device storage handle 24 hours of sensor data streaming? Match each question to the appropriate prototype fidelity format.
What was checked, without and with the skill
Checked
Without skill
With skill
Paper sketches are designated to test high-level navigation flow.
Passed
Passed
Clickable digital mocks are designated to test interactive tap accuracy on screen.
Missed
Passed
Code prototypes are designated to test technical data storage feasibility.
Passed
Passed
case-17 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md99 lines2 files
Design Thinking
Overview
Design Thinking is a human-centered approach to innovation that integrates user needs, technological feasibility, and business viability. Its five stages are iterative, not linear — expect to loop back as understanding deepens.
Framework
IRON LAW: Empathize BEFORE Define, Define BEFORE Ideate
Jumping to solutions (Ideate) without understanding the problem (Define)
wastes effort solving the wrong problem. Defining the problem without
empathizing with users produces internally-focused problem statements.
The sequence matters: understand the human first, then frame the problem,
then generate solutions.
The Five Stages
1. Empathize — Understand the user's world
Observe, interview, immerse in the user's context
Goal: understand needs, pain points, and motivations (not just what they say, but what they do and feel)
2. Define — Frame the right problem
Synthesize empathy findings into a Point of View (POV) statement:
[User] needs to [need] because [insight]
A well-defined problem is half-solved. Reframe if needed.
3. Ideate — Generate many solutions
Diverge: quantity over quality. Defer judgment.
Techniques: brainstorming, How Might We questions, SCAMPER, worst possible idea
Then converge: vote, cluster, select 2-3 concepts to prototype
4. Prototype — Make ideas tangible
Build quick, cheap, disposable prototypes to learn
Fidelity should match the question: paper sketches for flow, clickable mocks for interaction, code for technical feasibility