Of course, you can write your own prompts, but you can also ask Claude to do it for you. That's usually faster. In this guide you'll learn how.

By the end of this guide, you'll:

  • Have a Claude project dedicated to making prompts.
  • Make prompts quickly, based on your goal.
  • Build a personal prompt library.

Note: This builds on How to Write Effective Prompts for Claude (Part 1). You don't have to read it first, but if you do, you'll better understand the two kinds of prompt the builder produces: framework prompts and wizard prompts.

Why have Claude create your prompts?

Writing a structured prompt yourself takes time, especially if the framework prompts and wizard prompts from Part 1 are new to you. Claude can speed that up: you describe what you want, then it asks clarifying questions, works out the right structure, and writes the prompt.

That helps most with tasks you're not an expert in yourself. Claude can often judge what context is needed to do the task properly, and which approach works best to reach the result you want.

You're not outsourcing your thinking. You still decide what the prompt should deliver. You just don't have to start with an empty chat window and do all the research yourself.

Before you start

  • A Pro subscription is recommended.
  • You work in Cowork mode, not Chat mode. In this mode, Claude reads and edits files on your computer. Your library stays a local .md file that Claude works with directly.
  • Use the latest Opus model and set effort to High.

Make a prompt builder

1. Create a folder

Create a folder on your computer called "Prompt Library" and put this file in it:

  • The prompt library. Download the starter prompt library, with framework and wizard prompts plus the language-level components. Or start with an empty .md file.

The builder instruction goes in the project itself (next step), so the folder only needs the library.

2. Create a project and connect your folder

In a Project you group chats around one topic. Go to Projects and click New project.

Name the project Prompt Builder. Paste the instruction below into Instructions. It tells Claude how to build each new prompt:

<role_and_objective>
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.
</role_and_objective>

<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.
</context>

<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.
</instructions>

<process>
<step_1 goal="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).
</step_1>

<if_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 with XML tags, one tag per component.
4. Expand where useful: extra context or sources, steps, criteria, output rules (placement, length, structure, reading level).
</if_framework_prompt>

<if_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 with XML tags.
</if_wizard_prompt>

<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.
</both>
</process>

<output>
- Deliver the final prompt with XML tags.
- 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.
</output>

Under Local folder, choose the "Prompt Library" folder you just made. Set Visibility to Local so the project stays on your computer and Claude reads the folder as context. Leave Add files empty. The library already lives in the folder.

Note: Connecting the folder can make Claude rename the project to match it. Change the name back to Prompt Builder before you create it.

Then click Create project.

3. Build a prompt

For each new prompt, open a new chat inside the project in Cowork mode. Type:

I want to create a new prompt.

Claude reads the builder instruction and your library, then asks about your goal: what you want to achieve, who it's for, and the context you'll use the prompt in. A rough description is enough. In this example I asked for a brand story for the team, built step by step from three existing files.

From your answer, Claude picks the right type of prompt and explains why. Here it's a wizard prompt, because the brand story comes together over several steps. Before Claude writes the prompt, it asks a few follow-up questions, for example about the building blocks the brand story should contain.

Answer them, and Claude writes the prompt with XML tags. Read it through, give feedback, and have it adjusted until it's right.

Then test the finished prompt in a new chat outside the project, without the builder instruction and your library. That way you know the prompt works on its own. If something goes wrong, take your findings back to the project chat and sharpen the prompt further.

4. Save the prompt

Once the prompt is final, have Claude save it:

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

Claude adds the prompt to the bottom of the library file in the folder and confirms where it landed. Your existing prompts stay unchanged. No copying, pasting, or re-uploading.

Finally, rename the chat via Rename session, so you can scan the project easily. A name in the form Role / Goal works well. In this example that's Brand strategist / Brand story. That way each chat immediately shows which prompt came out of it.

That's how your library grows, with tested, structured prompts ready for the next task.

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

Share your experience

  • Do you think differently about writing prompts now?
  • Did the builder pick the right type of prompt for you?
  • What's your favorite prompt?

Coming up next?

You now know both kinds of prompt. And you have a builder that makes them for you whenever you need one. In the next part, you'll give Claude lasting context to work with by building an AI writing system. That starts with personas: the audiences Claude writes for, so it always knows who the text is meant for.