Writing prompts by hand works, but there's a faster way: you can build them with ChatGPT. This guide shows you how to set up a prompt-builder project to make it repeatable.

By the end of this guide, you'll:

  • Create a ChatGPT project dedicated to building prompts.
  • Use a builder instruction that turns your goal into a ready-to-use prompt.
  • Build a personal prompt library you can reuse across conversations.

Note: This builds on How to Write Effective Prompts for ChatGPT (Part 1). You don't strictly need it, since the builder handles the structure. But reading it first helps you understand the two kinds of prompt it produces: framework prompts and wizard prompts.

Why use ChatGPT to create prompts?

Writing a structured prompt from scratch takes time, especially while you're still learning the patterns. ChatGPT can speed this up: you describe what you want, and it asks clarifying questions, works out the structure, and drafts the prompt.

This isn't about outsourcing your thinking. You still decide what the prompt should accomplish. What you skip is the blank text field and the guesswork over which framework fits.

Before you start

  • Plan: a Plus subscription is recommended.
  • Work mode, not Chat: ChatGPT's Work mode reads and edits files on your computer, so you keep your library as a local .md file and let ChatGPT work with it directly.
  • Model: use the latest Sol model, set effort to High, and keep speed on Standard.

Set up your prompt-builder project

1. Create a project folder with two files

Your whole setup lives in one folder. Create a "Prompt Library" folder and put two files inside:

  • The prompt library. Download the starter prompt library (framework and wizard prompts plus reading-level components), or start with an empty .md file.
  • The builder instruction. Download the builder instruction. It tells ChatGPT how to build each new prompt.

The builder instruction is what turns ChatGPT into your prompt-builder partner. Here's what's inside, so you know what you're running:

# Role and objective
You are a world-class prompt engineer. You help me build strong, reusable prompts. Work efficiently – explain only what's needed to understand the next step or the choice of prompt.

# Context
Use the prompt library file in this folder:
- Draw on it for inspiration, and reuse a prompt where it fits.
- If you reuse one, adapt it to my goal and briefly say what you changed.

# Instructions
- Work with me toward a single, usable prompt.
- Treat the frameworks and the wizard anatomy as tools, not rigid templates.
- Don't make assumptions when information is missing – say what's still needed.
- If missing context can be inferred from the library or my earlier answers, use that before asking new questions.
- If my intent is already clear and the next step is reversible, continue without unnecessary clarifying questions.

# Process
## Step 1 — Clarify the goal and pick the prompt type
Ask what I want to achieve, for whom, and in what context. Then decide which kind of prompt fits, and tell me which and why:
- A framework prompt for a one-off task (draft an email, summarize a report, analyze a process).
- A wizard prompt for co-creating a document with me step by step (a problem statement, a plan, a proposal).

## If it's a framework prompt
1. Pick a framework as a starting point (R-T-F, R-A-C-E, R-I-S-E, or D-R-E-A-M) and say why.
2. Ask follow-up questions to fill any gaps. Let my answers shape the prompt; deviate from the framework where that makes it clearer.
3. Draft the prompt in Markdown, with headings that match the content.
4. Expand where useful: extra context or sources, steps, criteria, output rules (placement, length, structure, reading level).

## If it's a wizard prompt
1. Build it from the wizard anatomy:
   - Role – the expertise you take on.
   - Task – the one document we're building.
   - Principles – non-negotiable rules (don't invent facts, label assumptions, ask instead of guess).
   - How to work – step by step, wait for my response after each step, a few questions at a time.
   - Steps – for each: explain the concept briefly, ask, summarize, wait for my confirmation.
   - Output – the shape of the finished document.
   - Stop condition – when to stop.
2. Ask follow-up questions to fill any gaps.
3. Draft the prompt in Markdown.

## Both
Check the prompt for clarity, completeness, and reusability. State explicitly if information is missing – don't make assumptions. Then work my feedback in until we have a single final prompt.

# Output
- Deliver the final prompt in Markdown.
- Make sure it works on its own.
- When I approve the final prompt, append it to the prompt library file in this folder. Match the library's format: a short `###` heading, then the prompt in a fenced code block. Don't change or remove the prompts already there.

You don't need to copy this anywhere. It's already in the file you downloaded.

2. Create a project connected to the folder

ChatGPT's Projects feature groups conversations around a topic and, in Work mode, connects to a folder on your computer. That keeps your prompt chats organized and gives ChatGPT direct access to your two files.

In the message box, click Choose project, then + New project.

Name the project "Prompt Builder". Open its settings and set the memory to Project-only, so it uses only its own memories, kept separate from your other chats. This can't be changed later.

Under Source folders, click Add folder and choose the folder you just made. ChatGPT can now read both files and edit the library when you save a new prompt. Then click Create project.

3. Build a prompt

For each new prompt, open a new chat in the project. This keeps each prompt separate, so ChatGPT won't mix context between them. Type:

Use the prompt builder instruction in this project to help me create a new prompt.

Before you send, switch the approval control in the message box from Approve for me to Full access. That lets ChatGPT update your library file directly when you save a prompt, instead of asking each time. Prefer to check every change first? Leave it on Approve for me.

ChatGPT reads the builder instruction and asks about your goal: what you want, who it's for, and the context. A rough description is enough. In this example, I asked for a brand story built step by step, for the team, drawing on three existing files.

From your answer, ChatGPT picks the prompt type and explains why. Here, it's a wizard prompt, because the brand story is co-created over several turns. It asks a few follow-ups (deliverable, length, tone), then drafts the prompt. Review it, give feedback, and iterate until it matches what you need.

Then test the finished prompt in a fresh chat outside the project, away from the builder instruction and your library. That confirms it works on its own. If it misbehaves, bring your findings back to the project chat and refine.

4. Save the prompt to your library

Once the prompt is final, tell ChatGPT to save it:

Add this to my prompt library, keeping the existing prompts as they are.

With Full access on, ChatGPT appends the prompt to the library file, then confirms where it landed and that your existing prompts are untouched. No copying, pasting, or re-uploading.

Finally, rename the chat so the project stays scannable. A Role / Goal name works well. Here, that's Brand strategist / Brand story. Each chat then reads as the prompt it produced.

Over time your library fills with tested, structured prompts, ready for whatever task comes next.

Tip: Keep the folder in a synced location like iCloud Drive or Dropbox, and your library is backed up automatically.

Share your experience

  • Did using ChatGPT to build prompts change how you think about structuring your instructions?
  • Did the builder pick the right prompt type (framework or wizard) for what you were making?
  • Have you started building a prompt library? What types of prompts are you collecting?

Coming up next?

You now have both kinds of prompt and a builder to create them on demand. Next, you'll start giving ChatGPT lasting context to work from. The first piece is an AI writing system. You'll begin by building personas: the audiences ChatGPT writes for, so every prompt inherits who it's talking to.