Help us improve
Share bugs, ideas, or general feedback.
From pm-copilot
Use 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. This is the prompt generation skill; for guidance on using AI coding tools, use prototyping/vibe-coding.
npx claudepluginhub productfculty-aipm/pm-copilot-by-product-facultyHow this skill is triggered — by the user, by Claude, or both
Slash command
/pm-copilot:prototype-promptThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
Use this skill when the user asks to "create a prototype spec", "write a prompt for v0", "write a vibe-coding prompt", "turn this PRD into a prototype prompt", "create a Bolt prompt", "help me prototype this", "write a spec for Lovable", or wants to convert a PRD or feature description into a self-contained prompt that can be dropped directly into v0, Bolt, Lovable, or another AI coding tool. Also auto-invoked at the end of /write-prd to generate the prototype appendix.
Builds throwaway prototypes to answer design questions — terminal apps for logic/state exploration or multiple UI variations on a single route.
Builds a throwaway prototype to answer a design question — either a terminal app for state/logic exploration or multiple UI variations on a single route. Use when sanity-checking a data model, mocking up a UI, or exploring design options.
Share bugs, ideas, or general feedback.
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.
Read memory/user-profile.md for product context. Read the PRD, feature description, or user stories provided.
From the input, identify:
Format the prompt for maximum clarity:
# [Feature Name] Prototype
## Context
Product: [Product name]
User: [Primary persona in one sentence — who they are and what they're trying to accomplish]
Goal: Build a [happy path only] interactive prototype.
## Screens to build
### 1. [Screen Name]
- What it shows: [Content and data displayed]
- What the user can do: [Interactions available]
- Next state: [What happens when they take the main action]
### 2. [Screen Name]
- What it shows: [...]
- What the user can do: [...]
- Next state: [...]
### 3. [Success/Outcome Screen]
- What it shows: [What the user sees when they've completed their goal]
## User flow (happy path)
1. User arrives at [Screen 1]
2. User [action]
3. [Screen transition]
4. User [action]
5. User reaches [Outcome Screen]
## Mock data
Use these realistic examples (no placeholder text):
- [Example 1]
- [Example 2]
- [Example 3]
## Do NOT build
- Authentication or login flows (start already logged in)
- Error states or validation messages
- Empty states
- Settings or configuration pages
- Mobile responsive layout [unless this IS a mobile prototype]
- Admin or internal views
- [Any other specific exclusions from the PRD out-of-scope section]
## Technical requirements
Framework: React with functional components and hooks
Styling: Tailwind CSS
Data: Hardcoded mock data — no API calls, no backend
Navigation: Use React Router or simple state for screen transitions
Focus: Interaction flow over visual polish. The prototype should be functional, not pixel-perfect.
## Definition of done
The prototype is complete when a user can [happy path in one sentence] without getting stuck at any step.
For v0 (vercel.com/v0):
For Bolt (bolt.new):
For Lovable (lovable.dev):
For Claude Artifacts (conversational/AI features):
Produce: