Prototype Prompt logo

Prototype Prompt

Community
Productfculty-aipm
prototype-prompt

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.

Overview

PublisherProductfculty-aipm
RepositoryPM-Copilot-by-Product-Faculty
Skill nameprototype-prompt
Stars
80
Forks
34
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Productfculty-aipm on GitHub. Read the source before you install it.

Installation

Install the Prototype Prompt AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty/tree/main/skills/prototype-prompt
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty.git /tmp/PM-Copilot-by-Product-Faculty
mkdir -p .claude/skills
cp -r /tmp/PM-Copilot-by-Product-Faculty/skills/prototype-prompt .claude/skills/prototype-prompt
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prototype Prompt in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prototype Prompt on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prototype Prompt is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prototype Prompt Generator

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.

Step 1 — Load Context

Read memory/user-profile.md for product context. Read the PRD, feature description, or user stories provided.

Step 2 — Extract Required Information

From the input, identify:

  • Primary user (one sentence)
  • Core interaction (the one thing the user does)
  • Screens needed (list, with descriptions)
  • Happy path flow (step-by-step)
  • Realistic mock data (3–5 examples)
  • What to exclude (everything NOT in scope)
  • Target tool (v0, Bolt, Lovable, Cursor)

Step 3 — Generate the Prompt

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.

Step 4 — Tool-Specific Adaptations

For v0 (vercel.com/v0):

  • Add: "Output as a single React component with internal state management"
  • Works best: Single-screen interactions, React component libraries

For Bolt (bolt.new):

  • Add: "Create a complete Next.js application with the following pages"
  • Works best: Multi-screen apps, when you want generated file structure

For Lovable (lovable.dev):

  • Add: "Use a modern, clean design with subtle shadows and gentle animations"
  • Works best: Consumer-facing UIs where visual quality matters for user testing

For Claude Artifacts (conversational/AI features):

  • Replace the screen structure with: "Build an interactive conversation widget where..."
  • Add: "The AI responds to user input with [describe response pattern]"
  • Works best: AI-powered or conversational feature prototypes

Step 5 — Output

Produce:

  • The complete prompt, formatted and ready to paste
  • A brief note on what the first output is likely to need fixed (the most common first-iteration issues for this type of prototype)

Frequently asked questions

What does the Prototype Prompt AI skill do?

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.

Why use Prototype Prompt on TypingMind?

Because you install it once and use it with any model. Prototype Prompt is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prototype Prompt in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Productfculty-aipm/PM-Copilot-by-Product-Faculty/tree/main/skills/prototype-prompt. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Prototype Prompt?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prototype Prompt?

As many as you like. As long as a model supports skills, you can use Prototype Prompt with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prototype Prompt AI skill free?

It is published on GitHub by Productfculty-aipm. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇