# Skill: Design Thinking - Prototype ## Description Build rapid, low-fidelity prototypes to test solutions quickly and cheaply before full implementation. ## Input - **solution_idea**: The idea to prototype from ideate phase (required) - **fidelity_level**: low|medium|high (optional, default: low) - **components_available**: Existing UI components/patterns (optional) - **constraints**: Time/tech constraints (optional) ## Prototyping Approaches ### 1. Rapid MVP Patterns **Lo-Fi (1-2 hours):** - Paper sketches - Wireframes in Figma/Excalidraw - Clickable mockups - No code, just flows **Med-Fi (4-8 hours):** - Static HTML/CSS - Component prototypes - Fake data, real UI - Key interactions only **Hi-Fi (1-2 days):** - Working code prototype - Real component library - Actual data flow - Limited features, polished ### 2. Lo-Fi to Hi-Fi Progression **Stage 1: Sketch (30 mins)** ``` Purpose: Explore ideas fast Tool: Paper, whiteboard, Excalidraw Output: 3-5 rough layouts Decision: Pick one to refine ``` **Stage 2: Wireframe (1-2 hours)** ``` Purpose: Define structure & flow Tool: Figma, Balsamiq, HTML Output: Clickable wireframe Decision: Validate flow with users ``` **Stage 3: Visual Design (2-4 hours)** ``` Purpose: Define look & feel Tool: Figma with design system Output: High-fidelity mockups Decision: Validate aesthetics ``` **Stage 4: Code Prototype (4-8 hours)** ``` Purpose: Test technical feasibility Tool: React/Next.js components Output: Working prototype Decision: Ready for user testing ``` ### 3. Component-First Approach **Build from existing:** ```typescript // Start with proven components import { Button, Input, Card } from '@/components/ui' // Compose into new patterns function CampaignQuickCreate() { return ( ) } ``` **Component Inventory:** - List available UI components - Identify reusable patterns - Note what needs building - Prioritize existing over new ### 4. "Good Enough" Quality Gates **Lo-Fi Checklist:** - [ ] User can see the flow - [ ] Key interactions are clear - [ ] No polish needed - [ ] Can get feedback in <1 hour **Med-Fi Checklist:** - [ ] Looks like real product - [ ] Core interactions work - [ ] Uses design system - [ ] Good enough for user testing **Hi-Fi Checklist:** - [ ] Production-quality code - [ ] Accessible & responsive - [ ] Error states handled - [ ] Ready to ship (limited scope) ## Prototype Templates ### Quick Start Template ```typescript // Minimal prototype structure interface PrototypeProps { mode: 'demo' | 'interactive' } export default function Prototype({ mode }: PrototypeProps) { // 1. State (minimal) const [step, setStep] = useState(1) // 2. Key interactions only const handleNext = () => setStep(s => s + 1) // 3. Visual feedback return (
{step === 1 && } {step === 2 && } {step === 3 && }
) } ``` ### Paper Prototype Template ``` ┌─────────────────────────┐ │ Campaign Quick Create │ ├─────────────────────────┤ │ │ │ [Campaign Name____] │ │ │ │ [Template ▼] │ │ - Black Friday │ │ - Product Launch │ │ - Newsletter │ │ │ │ [Create Campaign] │ │ │ └─────────────────────────┘ Interactions: 1. Type name → enables template 2. Select template → preview 3. Click create → done (5 sec) ``` ## Output Format ```json { "status": "success", "prototype": { "type": "medium_fidelity", "time_spent": "6 hours", "tools_used": ["Figma", "React", "Tailwind"], "url": "https://prototype-link.com", "components_reused": ["Button", "Input", "Card", "Select"], "components_created": ["QuickCreateFlow"] }, "key_features": [ "1-click template selection", "Auto-filled campaign defaults", "5-second creation flow", "Inline preview" ], "limitations": [ "Only 3 template types", "No advanced customization", "Fake data backend" ], "testing_scenarios": [ { "scenario": "Create campaign from template", "steps": ["Select template", "Enter name", "Click create"], "expected_time": "5 seconds", "success_criteria": "Campaign created without errors" } ], "next_step": "Test with users using /dt test" } ``` ## Quality Gates - [ ] Built in <8 hours (for med-fi) - [ ] Core flow works end-to-end - [ ] Uses existing components where possible - [ ] Good enough for user feedback - [ ] Testing scenarios defined - [ ] Known limitations documented ## Token Budget - Max input: 1000 tokens - Max output: 1500 tokens ## Model - Recommended: sonnet (creative problem-solving) ## Philosophy > "Perfect is the enemy of good. Ship the prototype." > Fast feedback beats perfect implementation. **Keep it simple:** - Build minimum to test hypothesis - Reuse > rebuild - Speed > polish - Learn > perfect - Fake it till you make it (use mock data)