Design Agent Skill
Design Thinking process—Empathize, Define, Ideate, Prototype, Test. Use for product design, solving ambiguous problems, or when you don't know what users really need.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/neurofoo/agent-skills --skill designThe instruction itself
18 sections, as written by the authorDesign Thinking Process
Work through the full design thinking process—Empathize, Define, Ideate, Prototype, Test.
Instructions
Move through each phase, building on insights from the previous one. The process is iterative—expect to loop back based on what you learn.
Output Format
Challenge: [What we're trying to solve]
Users: [Who we're designing for]
1. EMPATHIZE
*Understand the user and their context*
User Profile
| Attribute | Description |
|-----------|-------------|
| Who are they? | [Demographics, role] |
| What's their context? | [Environment, circumstances] |
| What are they trying to do? | [Goals, tasks] |
User Pain Points
| Pain Point | Severity | Current Workaround |
|------------|----------|-------------------|
| [pain] | High/Med/Low | [how they cope] |
Empathy Map
| Quadrant | Observations |
|----------|--------------|
| Say | [Quotes, statements] |
| Think | [Beliefs, concerns] |
| Do | [Actions, behaviors] |
| Feel | [Emotions, reactions] |
2. DEFINE
*Frame the problem worth solving*
Point of View Statement
[User] needs [need] because [insight].
How Might We Questions
- How might we [opportunity 1]?
- How might we [opportunity 2]?
Problem Statement
> The Challenge: [Specific, actionable problem to solve]
3. IDEATE
*Generate many possible solutions*
Ideas Generated
| # | Idea | Type |
|---|------|------|
| 1 | [idea] | Safe / Moderate / Wild |
| 2 | [idea] | Safe / Moderate / Wild |
| 3 | [idea] | Safe / Moderate / Wild |
Top Ideas to Prototype
| Idea | Why This One? | Feasibility |
|------|---------------|-------------|
| [idea] | [rationale] | High/Med/Low |
4. PROTOTYPE
*Make ideas tangible quickly*
Idea to prototype: [Which idea]
Prototype type: Paper mockup / Wireframe / Physical model / Storyboard
What we're testing:
- [Assumption/question 1]
- [Assumption/question 2]
5. TEST
*Learn from real users*
Who to test with: [User profile]
Questions to answer:
- [Question]?
- [Question]?
Success indicators: [What would indicate this works]
Failure indicators: [What would indicate this fails]
Next Iteration
Based on what we learn, we'll likely need to revisit:
- [ ] Empathize / [ ] Define / [ ] Ideate / [ ] Prototype / [ ] Test
Guidelines
- Empathy is research, not assumption—talk to real users
- "How might we" keeps problems open and generative
- Prototype to think, not just to test
- Test early, test often, test cheaply
$ARGUMENTS
Other skills for the same job
different authors, same section of the catalogue
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when implementing any feature or bugfix, before writing implementation code
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
How to use it
Take neurofoo/design from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.