Brooke Wright
Brooke Wright · @wright_mode
FREE PROMPT PACK

Make your AI writing sound like a person

Three prompts. The second one is the bit everyone skips — you point the model at Wikipedia's own field guide to AI writing tells and tell it to avoid every single pattern on the list. Then you make it permanent so you never have to ask again.

3 copy-paste prompts ChatGPT or Claude The Wikipedia link Reusable skill included
Something went wrong. Please try again.

No spam. Unsubscribe anytime.

Three prompts that stop your writing reading like a chatbot wrote it Jump to the prompts → Join the Membership
Wright Mode — Free Resource

Stop your AI writing sounding like AI slop

Three prompts, in order. The middle one hands the model Wikipedia's own catalogue of AI writing tells and tells it to avoid every pattern on the list. That's the step almost everybody skips.

3 copy-paste prompts ChatGPT or Claude Before & after included Reusable skill file

What's inside

Run them in order in the same chat. Prompt one sets the intention, prompt two gives it the actual rules, prompt three makes it stick so you never do this dance again. Works the same in ChatGPT and in Claude.

1

Tell it what you want

The obvious one. On its own it gets you maybe halfway — the model sounds a bit more relaxed for two paragraphs and then drifts straight back into press-release voice. Do it anyway; it sets up prompt two.

From now on, humanise everything you write for me so it doesn't read as AI-generated. That means: - Vary my sentence length properly. Some long. Some four words. - Use contractions the way people actually speak - Let a sentence start with And, But or So when that's how it would land out loud - Cut every adjective that isn't earning its place - Say the thing plainly instead of building up to it - No summary paragraph at the end that just restates what you already said Confirm you've got it, then apply this to everything from here on without me asking again.
2

Give it the actual list

Here's the step nearly everybody misses. Wikipedia's editors have spent years cataloguing exactly how AI writing gives itself away — because they have to spot it every day. That catalogue is public. You hand it over and say "don't do any of this".

Read this page in full: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing It's Wikipedia's own field guide to how AI-generated text gives itself away — written by the editors who spot it for a living. Do three things: 1. Extract EVERY pattern it lists. Not a summary of the highlights — the full set, including the language ones, the style ones, the structural ones and the punctuation ones. 2. Turn that into a checklist of rules for your own writing, phrased as "never do X, do Y instead". 3. Apply all of it to everything you write for me from now on, permanently. Then show me the checklist so I can see what you're actually working from. Two things to hold on to as you do it: - Don't overcorrect into something stilted. Avoiding these patterns should make the writing sound MORE like a person, not less. - Some items on that page are specific to Wikipedia's house style (title case in headings, table formatting, citation habits). Skip those. Keep the ones that are about how the sentences read.
3

Make it permanent

Right now this only lives in one chat. Next conversation, you're back to square one. Turn it into a skill and it loads itself every time.

Now turn that checklist into a reusable skill called "humaniser" so I never have to set this up again. Write me a complete SKILL.md file containing: - A name and a one-line description of when it should trigger (any time I ask for writing of any kind) - The full rules list from the Wikipedia checklist, written as clear instructions - A short "before and after" example of each of the three worst offenders, so the rules are demonstrated rather than just stated - A final self-check the skill runs before it hands me anything: read the draft back and flag any line that still trips one of the rules Give it to me as one block I can copy straight into a file.

Bonus: audit something you already wrote

Got a draft that feels off but you can't say why? This one marks it up rather than rewriting it, so you learn the tells yourself.

Here's a draft: [PASTE YOUR TEXT] Using the Wikipedia AI-tells checklist, audit it. Do NOT rewrite it yet. For every line that trips a rule: - Quote the line - Name the pattern it's tripping - Show me the fix as a rewritten line At the end, tell me which single pattern I lean on most — that's my personal tell, and knowing it is worth more than any rewrite. Then, and only then, give me the full corrected version.

The page is Wikipedia:Signs of AI writing, maintained by the volunteers of WikiProject AI Cleanup — people who wade through undisclosed AI submissions daily and have got very good at spotting them. It's not a policy document and it's not trying to sell you anything. It's a field guide, and it's the most useful thing on this subject anywhere on the internet.

A taste of what's on it, so you know what you're handing over:

Puffed-up significance Promotional tone Vague attribution The rule of three Negative parallelism Em dash overuse Elegant variation Boldface everywhere Inline-header lists Emoji as formatting Curly quotes Tidy "future prospects" endings

Negative parallelism

"It's not just X, it's Y." Once you've seen it you'll see it eleven times a day. Models adore this construction and humans rarely reach for it twice in one paragraph.

The rule of three

Three neat items where two or four would be honest. "Practical, powerful and proven." Real speech isn't that tidy — the third item is usually there for rhythm, not meaning.

Inflated significance

Everything is described as marking a shift, reflecting a broader trend, or underscoring the importance of something. A human just says what happened.

Vague attribution

"Experts say", "many argue", "it is widely regarded as". No named source, because there isn't one. This is the tell that actually damages your credibility.

The wrap-up nobody asked for

The closing paragraph about challenges and future prospects. You didn't ask for a conclusion. It wrote one anyway, because it's been trained on essays.

Stock phrases

"Stands as a testament to". "Plays a vital role in". "Underscores the importance of". Individually harmless. Stacked up in one page, they're a signature.

Why this works better than "write more casually"

"Sound more human" is a vibe, and models are hopeless with vibes. A named list of twelve specific patterns is a rule set — something a model can genuinely check itself against. You're swapping an adjective for a specification, and that's the whole trick.


Same brief both times: a short paragraph introducing a workshop on AI for small business owners.

Before

"In an era where artificial intelligence is rapidly transforming the business landscape, small business owners face both unprecedented opportunities and significant challenges. This workshop is designed to help you chart a course through this complex terrain with confidence, clarity and competence. It's not just about learning the tools — it's about fundamentally reimagining how your business operates. Experts agree that early adopters will be best positioned to thrive in the years ahead."

After

"Most small business owners I meet have opened ChatGPT once, felt vaguely disappointed, and closed it again. Fair enough. Nobody showed them what it's actually for. This workshop is three hours of doing, not watching — you'll leave with two things running in your business that weren't running this morning. Bring the task you hate most. We'll start there."

Count what changed. The before opens with "in an era where" and never recovers. It's got a rule of three ("confidence, clarity and competence"), a negative parallelism ("it's not just about X — it's about Y"), a vague attribution ("experts agree") and a future-prospects sign-off. Four textbook tells in one paragraph, and not a single concrete detail anywhere.

The after says who it's for, what happens, how long it takes, and what to bring. It's shorter. It's also the only one of the two that would make somebody sign up.

The test that actually matters

Read it out loud. Not skim it — say it. If you'd never say that sentence to a friend in a kitchen, it isn't your writing yet. This test costs nothing and beats every detector on the market.


A skill is a folder with a SKILL.md file in it that the model reads before it starts working. Set it up once and every future chat already knows the rules — no re-prompting, no forgetting halfway through a long draft.

1

Get the file

Run prompt three above and it writes the SKILL.md for you, tailored to the checklist it extracted.

2

Put it somewhere the model looks

Claude Code or Claude Desktop: save it as ~/.claude/skills/humaniser/SKILL.md and restart. On claude.ai or Cowork: Customize → Skills → Add → Upload a skill. In ChatGPT, the same rules go into your custom instructions or a Project's instructions.

3

Now build the second one

The humaniser stops you sounding like a robot. It doesn't make you sound like you. That's a separate skill, and it's the one that actually matters.

I want to build a brand-voice skill to run alongside my humaniser skill. Here are 5 things I've written that genuinely sound like me: [PASTE 5 REAL SAMPLES — EMAILS, CAPTIONS, MESSAGES TO CLIENTS. NOT YOUR POLISHED WEBSITE COPY. THE ONES YOU BASHED OUT IN TWO MINUTES ARE THE MOST USEFUL.] Analyse them and tell me: 1. My average sentence length, and how much it varies 2. Words and phrases I reach for repeatedly 3. How I open — do I set up context first, or lead with the point? 4. How I handle humour, and how often 5. What I never do (words I avoid, punctuation I don't use, structures I never reach for) 6. My register — where I sit between "mate at the pub" and "consultant in a meeting" Then write a brand-voice SKILL.md from that analysis. Include real quotes from my samples as reference examples, not invented ones. Last instruction: this skill runs AFTER the humaniser. Humaniser strips out the AI patterns; this one puts me back in. Make sure the file says that explicitly.

Two skills, one after the other

Humaniser removes the tells. Brand voice adds you. Run only the first and you get clean, competent writing that could belong to anyone — which is better than AI slop, but it still isn't yours.


This genuinely works. Here's what I'd want you to know before you go and tell someone your writing scores 0% AI.

Detector scores prove almost nothing

I've had text come back at 0% AI-generated, and that's a nice feeling — but AI detectors are unreliable in both directions. They flag entirely human writing as machine-made (it happens to non-native English speakers constantly, and to anyone with a tidy writing style), and they wave through AI text that's been lightly edited. Wikipedia's own guide opens by warning people off relying on them. Treat a score as a smell test, never as evidence, and never send one to a client as proof of anything.

Some of that Wikipedia page isn't about you

It's written for spotting AI in Wikipedia articles, so a chunk of it is house-style specific — title case in headings, table formatting, citation conventions. Prompt two tells the model to skip those, but glance at the output checklist. If it's started refusing to use bold text anywhere, it's over-applied a Wikipedia rule to your newsletter.

Humanised is not the same as true

All of this changes how the writing sounds. None of it changes whether the writing is right. A confidently wrong sentence in a warm conversational voice is more dangerous than one in stiff corporate prose, because you're less likely to squint at it. Fact-check exactly as hard as you did before.

Don't strip out your own style

Em dashes are on the list, and I use them constantly — as you may have noticed. The tell isn't the em dash, it's five of them in one paragraph doing the same job. Same with lists of three: they're fine, they're just not fine four times a page. Aim for sounding like yourself, not for scoring zero on a checklist.

It drifts on long jobs

Halfway through a 2,000-word draft the model slips back into old habits without telling you. That's the whole argument for making it a skill rather than a prompt — but even then, on anything long, drop in "check that against the humaniser rules and fix what's slipped" before you accept the final draft.


Ready to go deeper?

Here's where to go if you want more of this.