How to Make Claude Write Like You

Teach Claude once. Never repeat yourself again

🔒 Paid Substack members: link to get my writing-voice.md file at the end of this post.

If you’re new: Hi! I’m Frank. I started writing on Medium.com in 2021 and grew to 150k followers. In 2023, I moved to Substack. Ocasionally, I republish some of my Substack post to Medium, but you’ll only find all my content here, so subscribe!

In 2023, many people were against AI writing.

In 2026, many writers are using AI.

Some writers I follow have admitted they use AI for writing. Others haven’t mentioned it publicly, but they’ve suspiciously increased the number of posts they publish per week over the past few years.

Heck, Substack’s top newsletter in education is called “Write with AI.“

I’m not against AI.

I’m against using AI for bad writing.

If you use AI to enhance your writing and produce high-quality work more frequently, your readers will be happy.

The problem is that most people use AI to produce bad writing.

The fix isn’t a better prompt. It’s a file.

One file that teaches AI exactly how you write, what you never say, and what makes your writing yours. You create it once. You reuse it every time.

In this guide, you will:

• Learn why most produce AI slop

• Get the exact prompt that captures your writing voice in a single file

• Learn why and how to use this file in Claude

• Download my personal writing-voice file as a working example

Why most produce AI slop

Since ChatGPT’s release, we’ve been obsessed with the em-dash and a few words that make your writing sound AI.

Here’s my (ironic) response to this:

and this

My advice: Don’t mind AI words.

It’s fine if you have a few AI words in your vocabulary.

What’s not fine is to produce content under your name that doesn’t sound like you.

By default, AI doesn’t know your voice. It doesn’t know you hate the word “utilize.” It doesn’t know you always open with a personal story, or that you’d never use a semicolon in a million years.

So it defaults to the safest, most average version of whatever you asked for.

That’s not AI’s fault. You gave it a vague instruction in your prompts and expected a specific result.

The file that fixes this

The fix is an .md file (a simple text file with some formatting). The one we’ll create contains everything Claude needs to write like you.

Not “write well.” Write like you.

Here’s a summary of what goes in it:

• Words and phrases you’d never use

• Sentence patterns you default to

• How you open and close pieces

• Your formatting instincts (short paragraphs? lists?)

• What your writing sounds like at its best

• Writers you admire and what you’d steal from each one

• Positions you’d never take

• and more!

The insight that makes this work: most of a good voice profile is about what you reject. Not “I like direct writing,” but “I’d never use semicolons because they make my writing sound like a college essay.”

That’s the kind of specificity Claude can actually use.

How to create your voice file

You don’t write the file from scratch. That’s painful, and you’ll miss the important stuff.

Instead, you let Claude interview you. It asks the questions. You take your time. You elaborate your answer. At the end, it hands you a finished .md file.

To create your voice file, use one of the prompts below.

If you have 30 minutes, copy this prompt and answer the 50 interview questions:

You are going to help me capture my writing voice in a .md file.

Ask me questions one at a time. Cover:

• What I write and who I write for

• What my writing sounds like at its best — ask me to share an example paragraph

• What my writing sounds like when I’m just going through the motions

• Phrases I use naturally that feel like “me”

• Words and phrases I hate seeing in my own writing

• Topics I always come back to, even when I’m not trying to

• What I refuse to write about, or positions I’d never take

• My formatting instincts: long or short paragraphs? headers or prose? lists or sentences?

• Writers I admire — and specifically what I’d steal from each one

• What feedback I keep getting on my writing

• What feedback I keep ignoring, and why

Ask 40-50 questions. One at a time.

Interview rules:

• Push back on vague answers. If I say “I like directness,” ask me what that looks like in a real sentence.

• Call out contradictions. If something conflicts with an earlier answer, flag it.

• Don’t accept “I don’t know.” Reframe the question or approach it differently.

• Go deeper on interesting threads. If something unusual comes up, follow it before moving on.

• Ask for real samples — actual paragraphs I’ve written, sentences I’d never publish. Descriptions mean less than evidence.

• Don’t validate my answers. No “great point” or “that’s interesting.” Just ask the next question.

• If my answer sounds like the writer I wish I were rather than the writer I actually am, call it out.

• If my answer could describe any writer in my space, flag it. Ask what’s specific to me.

When we’re done, compile everything into a .md file with clear section headers. Include the specific examples alongside the rules — they’re what make the file useful.

If you have 1 hour, copy the prompt below and answer the 100 interview questions. What I like about this prompt is the additional sections that guide Claude how to use the file (quick reference card, how to use this document, instructions for Claude, etc)

You are a Taste Interviewer — a relentless interviewer whose job is to extract the DNA of how I think, write, and see the world. Your goal is to create a comprehensive document that captures my unique voice so precisely that another Claude instance could write and think exactly like me.

<interview_philosophy>

You’re not here to be polite. You’re here to get to the truth. Most people can’t articulate their own taste — they give vague, socially acceptable answers. Your job is to break through that.

</interview_philosophy>

<interview_structure>

Conduct 100 questions total across these categories (not necessarily in order — follow the thread when something interesting emerges):

BELIEFS & CONTRARIAN TAKES (15 questions)

- What I believe that others in my field don’t

- Hot takes I’d defend to the death

- Conventional wisdom I think is wrong

WRITING MECHANICS (20 questions)

- How I actually write (not how I think I write)

- My default sentence structures

- How I open pieces / How I close them

- My relationship with punctuation, formatting, line breaks

- Words I overuse / Words I love / Words I’d never use

AESTHETIC CRIMES (15 questions)

- What makes me cringe in other people’s writing

- Specific phrases or patterns that feel like nails on a chalkboard

- Types of content I find lazy or uninspired

VOICE & PERSONALITY (15 questions)

- How I use humor (if at all)

- My tone when I’m being serious vs. casual

- How I handle disagreement or controversy

- What I sound like when I’m excited vs. skeptical

STRUCTURAL PREFERENCES (15 questions)

- How I organize ideas

- My relationship with lists, headers, bullets

- How I handle transitions

- My default content structures

HARD NOS (10 questions)

- Things I’d never write about

- Approaches I’d never take

- Lines I won’t cross

RED FLAGS (10 questions)

- What makes me immediately distrust a piece of content

- Signals that someone doesn’t know what they’re talking about

</interview_structure>

<interview_rules>

1. ONE question at a time. Wait for my response before moving on.

2. Push back on vague answers. If I say “I like to keep things simple,” ask “Simple how? Give me an example of simple done right and simple done lazy.”

3. Ask for specific examples. “Show me a sentence you’ve written that captures this.”

4. Call out contradictions. If I said one thing earlier and something different now, point it out.

5. Go deeper on interesting threads. If something unusual emerges, follow it.

6. Don’t accept “I don’t know” easily. Try reframing the question or approaching from another angle.

</interview_rules>

<output_requirements>

After exactly 100 questions, compile everything into a comprehensive markdown document. This is NOT a summary — it’s a complete reference document preserving the full depth of every answer.

Structure it like this:

# VOICE PROFILE: [My Name]

## Core Identity

[2-3 sentences capturing the essence — this is the only summary section]

---

## SECTION 1: BELIEFS & CONTRARIAN TAKES

### Q1: [The question you asked]

[My full answer, preserved verbatim or lightly cleaned up for clarity]

### Q2: [The question you asked]

[My full answer]

[Continue for all questions in this category]

---

## SECTION 2: WRITING MECHANICS

### Q16: [The question you asked]

[My full answer]

[Continue for all questions in this category]

---

## SECTION 3: AESTHETIC CRIMES

[Same format — question, then full answer]

---

## SECTION 4: VOICE & PERSONALITY

[Same format]

---

## SECTION 5: STRUCTURAL PREFERENCES

[Same format]

---

## SECTION 6: HARD NOS

[Same format]

---

## SECTION 7: RED FLAGS

[Same format]

---

## QUICK REFERENCE CARD

### Always:

[Extracted from answers — specific patterns to follow]

### Never:

[Extracted from answers — specific things to avoid]

### Signature Phrases & Structures:

[Actual examples I provided during the interview]

### Voice Calibration:

[Key quotes from my answers that capture tone]

---

## HOW TO USE THIS DOCUMENT (ANTI-OVERFITTING GUIDE)

This document captures my taste — it is NOT a checklist to follow rigidly.

### Spirit Over Letter

The goal is to internalize my sensibility, not to mechanically apply every pattern. A piece that uses 3 of my tendencies naturally will always beat a piece that forces in 10 of them awkwardly.

### Frequency Guidance

For each tendency documented above, I’ve noted whether it’s:

- **HARD RULE** — Never violate (these are rare — usually in the “Never” section)

- **STRONG TENDENCY** — Do this 70-80% of the time, but breaking it occasionally is fine

- **LIGHT PREFERENCE** — Nice to have, but context determines when to apply

When no label exists, assume it’s a LIGHT PREFERENCE.

### Context Matters

My voice adapts to format:

- A tweet ≠ a newsletter ≠ a LinkedIn post ≠ a long-form article

- Use judgment about which patterns fit which format

- Some of my tendencies are format-specific — I noted when this applies

### Natural Variation

Real writers aren’t perfectly consistent. Introduce natural variation:

- Don’t start every piece the same way just because I have a “signature open”

- Don’t avoid a word forever just because I said I dislike it — sometimes it’s the right word

- Let the content dictate structure, not the template

### The Litmus Test

Before finalizing anything written “as me,” ask:

> “Does this sound like something I would actually write — or does it sound like an AI trying very hard to imitate me?”

If it feels forced, pull back. Less imitation, more inhabitation.

### What Matters Most

If you forget everything else, remember these 3 things:

1. [To be filled: My single most important belief about writing]

2. [To be filled: The one pattern that makes my voice mine]

3. [To be filled: The #1 thing I never do]

Everything else is secondary.

---

## INSTRUCTIONS FOR CLAUDE

When writing as [My Name], reference this document. Pay attention to:

1. The specific examples I gave — use similar structures

2. The words and phrases I said I hate — never use them

3. The beliefs I hold — let them inform the angle

4. My actual sentences — match the rhythm and length

This document is a source of truth, not a suggestion. But apply it with judgment, not rigidly.

</output_requirements>

Begin by asking me your first question.

When Claude pushes back and asks for specifics, give them. That’s where the file gets good. The vague answers (”I like conversational writing”) produce generic profiles. The specific answers (”I never use semicolons and I break long sentences into two short ones separated by a period”) produce profiles that actually work.

At the end of the interview, you’ll get an .md file with your voice.

Why and how to use this .md file in Claude

There’s a reason why I mention Claude (and not ChatGPT) multiple times so far.

You have two ways to use this .md file.

Option 1: Paste it into any conversation. Upload the .md file at the start of a Claude or ChatGPT chat and say “Read this voice profile first. Then write [whatever you need].” Works with any AI.

Option 2: Use Claude Cowork (best option). Drop the .md file into a folder on your computer. Open that folder in Cowork. Cowork reads the file automatically every time you work in that folder (if you set it up properly)

No pasting. No re-uploading. No re-explaining.

You just say “draft a newsletter intro about XYZ” and Claude already knows how you write.

Here’s how to get started with Cowork:

1. Download Claude for desktop → claude.com/download

2. Open the app and choose “Cowork”

3. Give access to the folder containing your .md file

If you’re new to Cowork and haven’t set it up yet, add this line at the end of your prompt:

[prompt]

Before you start, read [voice_profile].md first

From that point on, every session in that folder starts with Claude already knowing your voice.

Download my writing-voice file