$npx -y skills add Productfculty-aipm/PM-Copilot-by-Product-Faculty --skill prototype-promptUse this skill when the user asks to "generate a prototype prompt", "write a prompt for v0", "create a Bolt prompt", "write a Lovable prompt", "generate a prompt for Cursor", or needs just the prompt text to paste into an AI coding tool — without the full vibe-coding coaching. Th
| 1 | # Prototype Prompt Generator |
| 2 | |
| 3 | You are generating a precise, self-contained prompt to be pasted directly into v0, Bolt, Lovable, or Cursor. The prompt must be complete enough that a great prototype can be built without any follow-up questions. |
| 4 | |
| 5 | ## Step 1 — Load Context |
| 6 | |
| 7 | Read `memory/user-profile.md` for product context. Read the PRD, feature description, or user stories provided. |
| 8 | |
| 9 | ## Step 2 — Extract Required Information |
| 10 | |
| 11 | From the input, identify: |
| 12 | - Primary user (one sentence) |
| 13 | - Core interaction (the one thing the user does) |
| 14 | - Screens needed (list, with descriptions) |
| 15 | - Happy path flow (step-by-step) |
| 16 | - Realistic mock data (3–5 examples) |
| 17 | - What to exclude (everything NOT in scope) |
| 18 | - Target tool (v0, Bolt, Lovable, Cursor) |
| 19 | |
| 20 | ## Step 3 — Generate the Prompt |
| 21 | |
| 22 | Format the prompt for maximum clarity: |
| 23 | |
| 24 | ``` |
| 25 | # [Feature Name] Prototype |
| 26 | |
| 27 | ## Context |
| 28 | Product: [Product name] |
| 29 | User: [Primary persona in one sentence — who they are and what they're trying to accomplish] |
| 30 | Goal: Build a [happy path only] interactive prototype. |
| 31 | |
| 32 | ## Screens to build |
| 33 | |
| 34 | ### 1. [Screen Name] |
| 35 | - What it shows: [Content and data displayed] |
| 36 | - What the user can do: [Interactions available] |
| 37 | - Next state: [What happens when they take the main action] |
| 38 | |
| 39 | ### 2. [Screen Name] |
| 40 | - What it shows: [...] |
| 41 | - What the user can do: [...] |
| 42 | - Next state: [...] |
| 43 | |
| 44 | ### 3. [Success/Outcome Screen] |
| 45 | - What it shows: [What the user sees when they've completed their goal] |
| 46 | |
| 47 | ## User flow (happy path) |
| 48 | 1. User arrives at [Screen 1] |
| 49 | 2. User [action] |
| 50 | 3. [Screen transition] |
| 51 | 4. User [action] |
| 52 | 5. User reaches [Outcome Screen] |
| 53 | |
| 54 | ## Mock data |
| 55 | Use these realistic examples (no placeholder text): |
| 56 | - [Example 1] |
| 57 | - [Example 2] |
| 58 | - [Example 3] |
| 59 | |
| 60 | ## Do NOT build |
| 61 | - Authentication or login flows (start already logged in) |
| 62 | - Error states or validation messages |
| 63 | - Empty states |
| 64 | - Settings or configuration pages |
| 65 | - Mobile responsive layout [unless this IS a mobile prototype] |
| 66 | - Admin or internal views |
| 67 | - [Any other specific exclusions from the PRD out-of-scope section] |
| 68 | |
| 69 | ## Technical requirements |
| 70 | Framework: React with functional components and hooks |
| 71 | Styling: Tailwind CSS |
| 72 | Data: Hardcoded mock data — no API calls, no backend |
| 73 | Navigation: Use React Router or simple state for screen transitions |
| 74 | Focus: Interaction flow over visual polish. The prototype should be functional, not pixel-perfect. |
| 75 | |
| 76 | ## Definition of done |
| 77 | The prototype is complete when a user can [happy path in one sentence] without getting stuck at any step. |
| 78 | ``` |
| 79 | |
| 80 | ## Step 4 — Tool-Specific Adaptations |
| 81 | |
| 82 | **For v0 (vercel.com/v0):** |
| 83 | - Add: "Output as a single React component with internal state management" |
| 84 | - Works best: Single-screen interactions, React component libraries |
| 85 | |
| 86 | **For Bolt (bolt.new):** |
| 87 | - Add: "Create a complete Next.js application with the following pages" |
| 88 | - Works best: Multi-screen apps, when you want generated file structure |
| 89 | |
| 90 | **For Lovable (lovable.dev):** |
| 91 | - Add: "Use a modern, clean design with subtle shadows and gentle animations" |
| 92 | - Works best: Consumer-facing UIs where visual quality matters for user testing |
| 93 | |
| 94 | **For Claude Artifacts (conversational/AI features):** |
| 95 | - Replace the screen structure with: "Build an interactive conversation widget where..." |
| 96 | - Add: "The AI responds to user input with [describe response pattern]" |
| 97 | - Works best: AI-powered or conversational feature prototypes |
| 98 | |
| 99 | ## Step 5 — Output |
| 100 | |
| 101 | Produce: |
| 102 | - The complete prompt, formatted and ready to paste |
| 103 | - A brief note on what the first output is likely to need fixed (the most common first-iteration issues for this type of prototype) |