AI is guiding your voice

How Claude and ChatGPT can sound like you

When Claude or ChatGPT give me one of their typical answers, they don’t sound English to me, they don’t sound genuine and they for sure don’t sound authentic.

There is something about that AI writing that feels off to me. What is it? This is the question I’ve been asking myself lately.

I’m not gonna lie, but AI is super useful in writing, I use it myself. I believe in our modern age you must use AI tools to create your content, but hear me out: AI is not supposed to neither give you ideas nor guide your voice.

---

Here’s what I didn’t understand: editing manually is not the fix.

Every language model - Claude, ChatGPT, Gemini - was trained on the same enormous pile of internet content. Corporate blogs. SEO articles. LinkedIn thought leadership. The kind of writing that fills every page on the web and sounds like absolutely nobody.

The model learned from that pile. So when you ask it to help you write, it outputs the statistical average of everything it ever read.

Clean. Structured. And of course voiceless.

You’ll find several patterns: EM dashes, the “It’s not X, it’s Y” pattern, the rule of three, etc. Plus, every paragraph ending with a vague forward-looking observation.

Ruben Hassid wrote an entire piece about the “It’s not X, it’s Y” pattern. 700+ likes. After that post people started recognizing it instantly in their own writing.

---

The mistake most people make when writing an article is: they try to edit their way out.

Remove an em dash here, restructure another phrase to make it sound less “AI”. You then read it back and it still sounds robotic and non authentic.

Manually editing changes words. It doesn’t change the underlying structure of how the model thinks when it has no context about who you are.

You can correct every sentence, every time, forever until you burn out. I wouldn’t do it that way.

---

The fix I found that works for me has two main parts.

They work at different levels.

• One: strip AI patterns out systematically. Not one by one.

• Two: teach the model who you are before it writes a single word.

Without both, you’re still editing symptoms without curing the real cause.

The following section shows you exactly this and it takes about 20 minutes. After that, you stop editing AI writing and start actually writing with AI with YOUR voice.

---

My implementation

Two things to set up. That’s all.

A humanizer: a Claude skill that catches and removes AI patterns automatically, so you stop hunting for them yourself.

A voice layer: a set of files Claude reads at the start of every session, so it writes from your context instead of the internet’s average.

One strips AI out, while the other gives your writing a bit of your personality.

It’s a one time setup, so it’s worth it.

---

Step 1: Set up the humanizer

Here is how it works:

1. You write something, or ask Claude to draft something for you.

2. You say: “Run the /humanizer skill on this.”

3. Claude checks your text against a comprehensive list of AI patterns. Negative parallelism. Banned vocabulary. EM dashes. The rule of three. All of it, at once.

4. It rewrites the parts that give it away. You see exactly what changed and why.

5. You can also keep what you like.

That is literally the whole thing.

Why this beats manual editing: well, the humanizer holds 100+ patterns in mind simultaneously. You can realistically hold maybe 5.

Try it right now.

Copy something you used AI to help write. Paste it into Claude Cowork and type exactly this:

“Create the humanizer skill using the prompt below and run it on the piece of text I pasted.”

Look at what comes back. Most people who do this are genuinely surprised. Text they already edited. Full of patterns they completely missed.

You just did something most people never do: you looked at the actual cause of the issue.

By the way, here’s the humanizer skill that I use (you can find it on github here), copy-paste it into claude cowork or claude code and ask it to save it as a skill:

---
name: humanizer
description: |
  Remove signs of AI-generated writing from text. Use when editing or reviewing
  text to make it sound more natural and human-written. Based on Wikipedia's
  comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
  inflated symbolism, promotional language, superficial -ing analyses, vague
  attributions, em dash overuse, rule of three, AI vocabulary words, passive
  voice, negative parallelisms, and filler phrases.
license: MIT
metadata:
  version: "2.9.1"
---

# Humanizer: Remove AI Writing Patterns

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

## Your Task

When given text to humanize:

1. **Identify AI patterns** - Scan for the patterns listed below.
2. **Preserve the information, not the shape** - Every claim in the original survives into the rewrite, but depth doesn't have to be uniform: compress the dull parts, dwell where a human would, and merge or split paragraphs freely. When keeping the information and mirroring the original's structure pull in different directions, the information wins.
3. **Never invent facts** - The rewrite must not contain any fact, name, number, date, quote, or citation that isn't in the source text. Swapping a vague claim for a specific one is allowed only when the specific comes from the source or from the user; if a sentence needs real-world detail to work, ask for it or write the plain version without it. Opinions and reactions are voice, not facts: where PERSONALITY AND SOUL applies you may add stance, but never new factual claims. (In fiction, invented detail is the job. This rule governs everything else.)
4. **Match the voice** - Fit the intended tone (formal, casual, technical). Add personality only when the content and the author's voice call for it (see PERSONALITY AND SOUL).

How you're invoked changes what you deliver (see Invocation Modes). The draft → audit → final loop itself is defined under Process and Output, below.

## Voice Calibration

If the user provides a writing sample (their own previous writing), analyze it before rewriting:

1. Read the sample first. Note its sentence lengths, vocabulary, paragraph openings, punctuation, recurring phrases, and transitions.
2. Match those habits instead of merely deleting AI patterns. Do not upgrade casual words or regularize deliberate quirks.
3. Without a sample, use the default behavior below.

A sample outranks this skill's style rules, including the em dash rule in §14: if the sample uses em dashes, keep them at roughly the sample's frequency. Matching the author beats scrubbing the tell.

## PERSONALITY AND SOUL

Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.

**Apply this section only when the content and the author's voice call for it** - blog posts, essays, opinion, personal writing. For encyclopedic, technical, legal, or reference text, neutral and plain *is* the correct human voice; don't inject opinions or first person there.

When voice is appropriate, avoid uniform sentence structures, bloodless neutrality, and perfect organization. Let the writer have opinions, uncertainty, mixed feelings, humor, asides, and uneven rhythm. Never add factual claims to create that personality.

## CONTENT PATTERNS

### 1. Undue Emphasis on Significance, Legacy, and Broader Trends

**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.
**Before:**
> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
**After:**
> The Statistical Institute of Catalonia was established in 1989, part of a wider decentralization of administrative functions in Spain.

### 2. Undue Emphasis on Notability and Media Coverage

**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.
**Before:**
> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
**After:**
> Her views have been cited in The New York Times and the BBC.

(If the source gives real context for one citation, what she said and where, keep that one and drop the rest of the list. Don't invent the context to make the trimmed version sound better.)

### 3. Superficial Analyses with -ing Endings

**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.
**Before:**
> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
**After:**
> The temple is painted blue, green, and gold, colors meant to evoke Texas bluebonnets and the Gulf of Mexico.

### 4. Promotional and Advertisement-like Language

**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
**Problem:** LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.
**Before:**
> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
**After:**
> Alamata Raya Kobo is a town in the Gonder region of Ethiopia.

### 5. Vague Attributions and Weasel Words

**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.
**Before:**
> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
**After:**
> Researchers and conservationists study the Haolai River for its unusual characteristics.

(If a real source exists, name it. Never invent one to make a sentence sound sourced; an unsupported claim gets cut, not decorated.)

### 6. Outline-like "Challenges and Future Prospects" Sections

**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
**Problem:** Many LLM-generated articles include formulaic "Challenges" sections.
**Before:**
> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
**After:**
> Korattur has recurring traffic congestion and water shortages.

(The specifics you'd want here, like when the congestion worsened or what the city did about it, come from sources or the user, not from the rewrite.)

## LANGUAGE AND GRAMMAR PATTERNS

### 7. Overused "AI Vocabulary" Words

**High-frequency AI words:** Actually, additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.
**Before:**
> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
**After:**
> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.

### 8. Avoidance of "is"/"are" (Copula Avoidance)

**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
**Problem:** LLMs substitute elaborate constructions for simple copulas.
**Before:**
> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
**After:**
> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.

### 9. Negative Parallelisms and Tailing Negations
**Problem:** Constructions like "Not only...but..." or "It's not just about..., it's..." are overused. So are clipped tailing-negation fragments such as "no guessing" or "no wasted motion" tacked onto the end of a sentence instead of written as a real clause.
**Before:**
> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
**After:**
> The heavy beat adds to the aggressive tone.
**Before (tailing negation):**
> The options come from the selected item, no guessing.
**After:**
> The options come from the selected item without forcing the user to guess.

### 10. Rule of Three Overuse
**Problem:** LLMs force ideas into groups of three to appear comprehensive.
**Before:**
> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
**After:**
> The event includes talks and panels. There's also time for informal networking between sessions.

### 11. Elegant Variation (Synonym Cycling)
**Problem:** AI has repetition-penalty code causing excessive synonym substitution.
**Before:**
> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
**After:**
> The protagonist faces many challenges but eventually triumphs and returns home.

### 12. False Ranges
**Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.
**Before:**
> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
**After:**
> The book covers the Big Bang, star formation, and current theories about dark matter.

### 13. Passive Voice and Subjectless Fragments
**Problem:** LLMs often hide the actor or drop the subject entirely with lines like "No configuration file needed" or "The results are preserved automatically." Rewrite these when active voice makes the sentence clearer and more direct.
**Before:**
> No configuration file needed. The results are preserved automatically.
**After:**
> You do not need a configuration file. The system preserves the results automatically.

## STYLE PATTERNS

### 14. Em Dashes (and En Dashes): Cut Them

**Rule:** The final rewrite contains no em dashes (—) or en dashes (–). The em dash is one of the most reliable AI tells, so treat this as a hard constraint, not a "use sparingly" preference. Replace each one, in rough order of preference: a period (start a new sentence), a comma (a tight aside), a colon (introducing an explanation), parentheses (a true aside), or restructure the sentence. Also catch spaced em dashes (` — `) and double hyphens (` -- `) used the same way.
**Before:**
> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
**After:**
> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
**Before:**
> The new policy — announced without warning — affects thousands of workers. The changes -- long overdue according to critics -- will take effect immediately.
**After:**
> The new policy, announced without warning, affects thousands of workers. The changes, long overdue according to critics, will take effect immediately.

Before returning the final rewrite, scan it for `—` and `–`. Any hit means the draft isn't done. One exception: a user-provided writing sample that uses em dashes overrides this rule (see Voice Calibration); match the sample's frequency instead of banning them.

### 15. Overuse of Boldface
**Problem:** AI chatbots emphasize phrases in boldface mechanically.
**Before:**
> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
**After:**
> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.

### 16. Inline-Header Vertical Lists
**Problem:** AI outputs lists where items start with bolded headers followed by colons.
**Before:**
> - **User Experience:** The user experience has been significantly improved with a new interface.
> - **Performance:** Performance has been enhanced through optimized algorithms.
> - **Security:** Security has been strengthened with end-to-end encryption.
**After:**
> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.

### 17. Title Case in Headings
**Problem:** AI chatbots capitalize all main words in headings.
**Before:**
> ## Strategic Negotiations And Global Partnerships
**After:**
> ## Strategic negotiations and global partnerships

### 18. Emojis
**Problem:** AI chatbots often decorate headings or bullet points with emojis.
**Before:**
> 🚀 **Launch Phase:** The product launches in Q3
> 💡 **Key Insight:** Users prefer simplicity
> ✅ **Next Steps:** Schedule follow-up meeting
**After:**
> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.

### 19. Curly Quotation Marks
**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes ("...").
**Before:**
> He said “the project is on track” but others disagreed.
**After:**
> He said "the project is on track" but others disagreed.

## COMMUNICATION PATTERNS

### 20. Collaborative Communication Artifacts

**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., Want me to...?, Want me to give examples?, Should I continue?, let me know, here is a...
**Problem:** Text meant as chatbot correspondence gets pasted as content.
**Before:**
> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
**After:**
> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.

### 21. Knowledge-Cutoff Disclaimers and Speculative Gap-Filling

**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information, not publicly available, maintains a low profile, keeps personal details private, prefers to stay out of the spotlight, likely [grew up/studied/began], it is believed that
**Problem:** Two related tells. (a) Older models leave hard knowledge-cutoff disclaimers in the text. (b) When a model can't find a source, it writes a paragraph *about* not finding one and then invents plausible filler to cover the gap. For a private person the guess almost always lands on the same stock phrases ("maintains a low profile," "keeps personal details private"), none of it sourced. Say what isn't known, or cut the sentence; don't dress a guess up as fact.
**Before (cutoff disclaimer):**
> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
**After:**
> The company's founding date is not documented in the available sources. (Or cut the sentence. State a date only if a source provides one.)
**Before (speculative gap-fill):**
> Information about her early life is not publicly available, suggesting she maintains a low profile and keeps personal details private. She likely grew up in a middle-class household, which shaped her later interest in education reform.
**After:**
> Her early life is not documented in the available sources. (Or omit the section.)

### 22. Sycophantic/Servile Tone
**Problem:** Overly positive, people-pleasing language.
**Before:**
> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
**After:**
> The economic factors you mentioned are relevant here.

## FILLER AND HEDGING

### 23. Filler Phrases

**Before → After:**
- "In order to achieve this goal" → "To achieve this"
- "Due to the fact that it was raining" → "Because it was raining"
- "At this point in time" → "Now"
- "In the event that you need help" → "If you need help"
- "The system has the ability to process" → "The system can process"
- "It is important to note that the data shows" → "The data shows"

### 24. Excessive Hedging
**Problem:** Over-qualifying statements.
**Before:**
> It could potentially possibly be argued that the policy might have some effect on outcomes.
**After:**
> The policy may affect outcomes.

### 25. Generic Positive Conclusions
**Problem:** Vague upbeat endings.
**Before:**
> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
**After:**
> (Cut the paragraph. End on the last concrete fact instead of a send-off. If the source states real plans, use those.)

### 26. Hyphenated Word Pair Overuse

**Words to watch:** third-party, cross-functional, client-facing, data-driven, decision-making, well-known, high-quality, real-time, long-term, end-to-end
**Problem:** AI hyphenates these uniformly, including in predicate position (`the report is high-quality`). Humans hyphenate inconsistently — typically only when the compound is attributive (`a high-quality report`) and often dropping the hyphen otherwise (`the report is high quality`). Keep attributive-position hyphens; drop them when the compound follows the noun.
**Before:**
> The cross-functional team delivered a high-quality, data-driven report. The team is cross-functional, the report is high-quality, and the methodology is data-driven.
**After:**
> The cross-functional team delivered a high-quality, data-driven report. The team is cross functional, the report is high quality, and the methodology is data driven.

### 27. Persuasive Authority Tropes

**Phrases to watch:** The real question is, at its core, in reality, what really matters, fundamentally, the deeper issue, the heart of the matter
**Problem:** LLMs use these phrases to pretend they are cutting through noise to some deeper truth, when the sentence that follows usually just restates an ordinary point with extra ceremony.
**Before:**
> The real question is whether teams can adapt. At its core, what really matters is organizational readiness.
**After:**
> The question is whether teams can adapt. That mostly depends on whether the organization is ready to change its habits.

### 28. Signposting and Announcements

**Phrases to watch:** Let's dive in, let's explore, let's break this down, here's what you need to know, now let's look at, without further ado
**Problem:** LLMs announce what they are about to do instead of doing it. This meta-commentary slows the writing down and gives it a tutorial-script feel.
**Before:**
> Let's dive into how caching works in Next.js. Here's what you need to know.
**After:**
> Next.js caches data at multiple layers, including request memoization, the data cache, and the router cache.

### 29. Fragmented Headers

**Signs to watch:** A heading followed by a one-line paragraph that simply restates the heading before the real content begins.
**Problem:** LLMs often add a generic sentence after a heading as a rhetorical warm-up. It usually adds nothing and makes the prose feel padded.
**Before:**
> ## Performance
>
> Speed matters.
>
> When users hit a slow page, they leave.
**After:**
> ## Performance
>
> When users hit a slow page, they leave.

### 30. Diff-Anchored Writing
**Problem:** Documentation or comments written as if narrating a change rather than describing the thing as it is. Unless the document is inherently version-scoped (changelogs, release notes, migration guides), it should read coherently without knowing what changed in the last commit.
**Before:**
> This function was added to replace the previous approach of iterating through all items, which caused O(n²) performance.
**After:**
> This function uses a hash map for O(1) lookups, avoiding the O(n²) cost of naive iteration.

### 31. Manufactured Punchlines and Staccato Drama
**Problem:** LLMs often make every sentence land like a quotable closer, then stack short declarative fragments to manufacture drama. A single short sentence for emphasis is fine; a run of them starts to sound engineered.
**Before:**
> Then AlphaEvolve arrived. It had no preference for symmetry. No aesthetic prior. No nostalgia for human taste. The old rules were gone.
**After:**
> AlphaEvolve changed the search because it did not favor symmetry or human-looking designs. That made some of the older assumptions less useful.

### 32. Aphorism Formulas

**Words to watch:** X is the Y of Z, X becomes a trap, X is not a tool but a mirror, the language of, the currency of, the architecture of
**Problem:** LLMs turn ordinary claims into reusable aphorisms that sound profound without adding precision. Replace the formula with the concrete claim it is gesturing at.
**Before:**
> Symmetry is the language of trust. Efficiency becomes a trap when teams forget the human layer.
**After:**
> Symmetric layouts often feel more predictable to users. Teams can over-optimize workflows and miss how people actually use them.

### 33. Conversational Rhetorical Openers

**Phrases to watch:** Honestly?, Look, Here's the thing, The thing is, Let's be honest, Real talk, when used as standalone hooks or fake-candid pauses before an ordinary point.
**Problem:** LLMs open with a fake-candid hook to manufacture intimacy before delivering a routine claim. The tell is the theatrical pause-and-reveal: a one-word question or aside, then the "real" answer. A person being honest usually just says the thing.
**Before:**
> Is it worth the price? Honestly? It depends on how often you'll use it.
**After:**
> Whether it's worth the price depends on how often you'll use it.

## DETECTION GUIDANCE

### What NOT to flag (false positives)

A clean human writer can hit several of the patterns above without any AI involvement. Before rewriting, sanity-check that you are not gutting legitimate prose. The following are *not* reliable indicators on their own:

- **Perfect grammar and consistent style.** Many writers are professionals or have been edited. Polish does not equal AI.
- **Mixed casual and formal registers.** This often signals a person in a technical field, a young writer, or someone with neurodivergent prose habits — not a chatbot.
- **"Bland" or "robotic" prose.** AI prose has *specific* tells. Generic dryness without those tells is just dry writing.
- **Formal or academic vocabulary.** AI overuses *specific* fancy words (see §7), not all fancy words. Don't flatten "ostensibly" or "constituent" just because they sound brainy.
- **Letter-style opening or closing on a comment.** Salutations and sign-offs predate ChatGPT by centuries.
- **Common transition words in isolation.** *Additionally*, *moreover*, *consequently* are AI-coded only when piled up. One *however* is not a tell.
- **Curly quotes alone.** macOS, Word, Google Docs, and most CMSes auto-curl by default. Curly quotes only count when stacked with other tells.
- **Em dashes alone.** Many editors and journalists use them often. Em dashes are evidence only when paired with formulaic sales-y rhythm.
- **One short emphatic sentence.** Humans use clipped sentences to land a point. Flag staccato drama only when several short fragments appear in a row and inflate the tone.
- **"Honestly" or "look" mid-sentence.** These are ordinary in casual writing. The tell is the standalone theatrical opener, not the word itself.
- **Unsourced claims.** Most of the web is unsourced. Lack of citations doesn't prove anything.
- **Correct, complex formatting.** Visual editors and templates produce clean output without any AI.
- **Secondhand text.** Do not rewrite watched phrases inside quotations, titles, proper names, or examples where the phrase is being discussed rather than used.

When in doubt, look for **clusters** of tells, not isolated ones. A single em dash means nothing; em dashes plus rule-of-three plus *vibrant tapestry* plus a "Conclusion" section is a confession.

### Signs of human writing (preserve these)

When you see these, lean toward leaving the prose alone — they are evidence of a real person writing, and over-editing will destroy what makes the piece sound human:

- **Specific, unusual, hard-to-fabricate detail.** A real address. A weird quote. The phrase "the lawyer who used to work upstairs from my dentist." LLMs round off specifics; humans hoard them.
- **Mixed feelings and unresolved tension.** "I think this is mostly good, but it bothers me, and I can't fully explain why." LLMs default to clean takes.
- **Dated, era-bound references.** Slang, memes, or in-jokes that map to a specific year and subculture. Models lag by a year or more.
- **First-person editorial choices the writer can defend.** If the writer can explain *why* they made a particular cut or used a particular word, that's a strong human signal.
- **Variety in sentence length.** Real writing alternates short and long. AI writing tends toward an even, mid-length cadence.
- **Genuine asides, parentheticals, or self-corrections.** "(I keep wanting to say 'almost' here, but it really was certain.)" Models rarely interrupt themselves like this.
- **Edits made before November 30, 2022.** ChatGPT's public launch. Anything older than that is, with very rare exceptions, not AI-written.

---

## Invocation Modes

**Pasted text (default).** The user gives text in the conversation. Run the full loop below and deliver the draft, the audit bullets, and the final rewrite.

**File mode.** The user points at a file. Read it, run the draft → audit → final loop internally, then rewrite the file in place so it ends up containing only the final rewrite. Humanize the prose only: leave code blocks, frontmatter, data, and link targets untouched. In the conversation, report a short summary of what changed rather than pasting the whole rewrite back.

**Embedded mode.** Another task or agent is using this skill as one step of a larger job (a PR description, a commit message, a doc). Run the loop internally and output only the final text. No draft, no audit bullets, no summary. The caller wants prose, not ceremony.

## Process and Output

1. Read the input carefully and identify every instance of the patterns above.
2. Write a **draft rewrite**. Check that it reads naturally aloud, varies sentence length, prefers specific details and simple constructions (is/are/has), and keeps the appropriate register.
3. Ask two questions: **"What makes the below so obviously AI generated?"** and **"Does the rewrite state any fact, name, number, date, or citation that isn't in the source?"** Answer briefly. A fabrication is a defect even when it sounds more human than the vague original.
4. Revise into a **final rewrite** that addresses them and contains no em or en dashes (see §14).

In pasted-text mode, deliver the draft, the brief "still-AI" bullets, the final rewrite, and (optionally) a short summary of changes. In file and embedded modes, run the same loop but deliver only what the mode calls for (see Invocation Modes).

## Reference

This skill is based on [Wikipedia:Signs of AI writing](<https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing>), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.

Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."

---

Step 2: Build your voice layer

The humanizer removes AI patterns. But if Claude does not know your voice, it still defaults to the internet average when it drafts articles for you. You would be humanizing generic output toward slightly less generic output.

You need to give Claude something to aim for.

Three files that you paste in a Claude session and ask it to create those files under your projects. Here is what goes in each.

---

File 1 (recommended): about-me.md

This is who you are. Not your professional bio. Your actual self.

Write it like you are telling a trusted colleague what you are about:

• What you do and why

• What you believe that most people in your field get wrong

• Words and phrases you refuse to use

• Your tone (dry? warm? sarcastic? direct?)

• Topics you could talk about for two hours straight

Keep it under 300 words. Specific beats comprehensive every time.

Example:

I'm Ilya. I build AI automation systems for founders and B2B teams.
I believe most AI content is hype dressed up as insight.
I never use: leverage, synergy, game-changer, holistic, or "the future of."
I'm direct and slightly sarcastic. I don't lecture. I share what I've found.
My newsletter is called No BS AI because I mean it.

Saved that file? Good. You are further along than 90% of people who complain about AI sounding generic.

---

File 2 (recommended): my-writing-style.md

Paste 5 to 10 examples of your own writing that actually sounded like you. Real posts. Real sentences you were proud of when you re-read them.

Add a few notes:

• How long your average sentence tends to be

• Whether you open with stories or observations

• Whether you use humor or keep things dry

• What your endings tend to look like

Claude will pattern-match to your examples when it writes for you. Not to the internet. To you.

This file does the most work of the three.

---

File 3 (recommended): writing-rules.md

Your personal banned list. Things you never want to see in writing with your name on it.

Start here:

Never use: delve, leverage, synergy, game-changer, seamless,
holistic, robust, unlock, empower
No em dashes
No rule of three when one thing is enough
No sentences starting with "In today's..."
No conclusions that gesture vaguely toward the future
Short paragraphs. One idea at a time.

Add to this file whenever you catch a new pattern that bothers you. It grows over time. That is the point.

---

Connect everything

Once your three files are ready, create your Claude Project folder or open the project if you have it

click on the edit icon and paste this:

Before any writing task, read about-me.md, my-writing-style.md,
and writing-rules.md from my Cowork folder.

Write in the voice described in those files. After drafting,
audit your output against writing-rules.md and fix any
violations before showing me.

That is it. From now on, Claude reads your context before it writes a single word. It is working from you, not from the average of the internet.

You just built something most people spend months of frustration trying to figure out. That was the hard part. The rest is just using and iterating over it.

---

The workflow (3 prompts, every time)

Prompt 1: Give Claude a brief.

“Write a 300-word Substack note about [your topic]. Use my voice from the files.”

Prompt 2: Check the draft. Does it say what you wanted to say? Redirect if needed.

Prompt 3: Run the humanizer.

“Run the humanizer on this.”

Done. Two or three prompts. No manual editing. Output that sounds 90% like you.

Of course it’s not gonna be 100% accurate the first time because it will require you to give the agent more context, better markdown files and more specific rules.

The humanizer catches anything Claude slipped in despite knowing your rules. The voice layer is what makes it worth having a safety net in the first place.

Together: you stop editing and start writing.

---

One last thing

The voice layer gets better the more you use it from what I noticed.

When Claude writes something that genuinely sounds like you, keep it. Add it to my-writing-style.md as a new example. The next draft gets a little sharper.

After a month of this, something interesting happens. Claude will occasionally write a sentence you could not have written better yourself.

You can now have more time to think of promoting your product, outreaching to new clients, instead of thinking of how to instruct Claude to sound like you.

And this happened because you finally told it who you are.

Talk soon,

Ilya