Make AI writing sound like you (and pass every detector)
Build a permanent humanizer skill for Claude — one command, works forever.
Hey, it's Adam 👋 Here's the thing about AI detectors: they don't read your text for meaning. They measure statistical patterns — the same sentence structures over and over, the same filler phrases, the same punctuation habits. Remove those patterns and the text reads as human. This guide builds you a reusable Claude skill that humanizes everything you write. One command. Forever. And if you're using this for job applications, pair it with my AI job search system — a humanized cover letter hits different.
📬 Get guides like this in your inbox every Thursday
Read it here free, or subscribe and get every new one, plus the AI news that matters.
Detectors don't read. They measure. 📏
Wikipedia maintains a page called "Signs of AI writing" that catalogues every pattern AI detectors look for. We're going to feed that entire list to Claude, tell it to never do any of those things, and save it as a reusable skill.
What's a skill? A saved set of instructions Claude follows whenever you activate it. When you type /human (or just say "use my human skill"), Claude switches into humanizer mode and applies all the rules automatically. You build it once, install it, and it works forever. Skills work on every Claude plan, including Free, as long as Code execution and file creation is turned on in Settings → Capabilities.
The 4-step setup 🛠️
- 1Tell Claude to humanize your text — one prompt makes it read Wikipedia's full pattern list and confirm what it found.
- 2Verify the pattern list — check it found patterns in all four categories before moving on.
- 3Build the humanizer skill — turn everything into a permanent
/humancommand. - 4Install the skill — save it, and it's in your Claude setup for good.
Open Claude, start a new chat, and paste this:
I want you to humanize all my text moving forward so it doesn't sound like AI. Go to this Wikipedia page:en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writingRead through every single pattern listed on that page. From now on, never use any of those patterns in your writing. List out every pattern you found so I can confirm you understand them all.
Claude reads the page, pulls out all the patterns, and lists them back. Check the list — you don't need to copy the Wikipedia page yourself, Claude reads it straight from the URL.
Step 2 — verify. The patterns that matter for everyday writing fall into four categories: content (inflated significance, promotional language, vague attributions), language (AI vocabulary, copula avoidance, synonym cycling), style (em dash overuse, excessive bold, inline header lists), and communication (chatbot pleasantries, sycophantic tone, filler phrases). If anything's missing, tell Claude to go back and look again.
Step 3 — build the skill. Stay in the same chat and type:
/skill-creatorBuild me a personal humanizer skill based off everything we just found so I never have to explain any of this ever again. Name it 'human'. Make it activate when I type /human.
Step 4 — install. Claude generates the skill — save it with the button it shows you. If you get a skill file instead, download it, go to Customize → Skills, click + and upload it. Either way it's permanent. From then on, type /human at the start of any chat and write normally.
Stay in the same chat for all four steps. If you start a new chat between steps, Claude loses the context from the Wikipedia patterns and the skill won't include everything.
Every pattern that gets flagged 🚩
Here's what detectors look for, organized by category. Your humanizer skill will avoid all of it — but it's worth knowing the list yourself, because you'll start spotting these everywhere.
Content patterns — the way AI inflates and hypes:
| Pattern | What it looks like | The fix |
|---|---|---|
| Inflated significance | "Serves as a testament to..." "Pivotal moment in the evolution of..." | Just say what it is. Skip the importance puffing. |
| Undue notability claims | "Featured in The New York Times, BBC, and Wired..." | Cite one source with a specific detail. |
| -ing phrase padding | "Highlighting... Underscoring... Emphasizing..." | End the sentence. Start a new one. |
| Promotional language | "Vibrant" "Nestled" "Breathtaking" "Groundbreaking" | Use plain, specific descriptions. |
| Vague attributions | "Experts say..." "Industry observers note..." | Name the actual source or drop the claim. |
| Challenges and prospects | "Despite challenges... the future looks bright" | State specific facts. Skip the optimism. |
Language patterns — the vocabulary and sentence tics:
| Pattern | What it looks like | The fix |
|---|---|---|
| AI vocabulary words | "Delve" "Crucial" "Landscape" "Tapestry" "Foster" "Leverage" | Use normal words. "Look into" not "delve." |
| Copula avoidance | "Serves as" "Stands as" "Boasts" instead of "is" or "has" | Just say "is" or "has." |
| Negative parallelisms | "It's not just X, it's Y" "Not only... but also..." | State the point directly. |
| Rule of three abuse | "Innovation, inspiration, and industry insights" | Don't force three items. Two or four is fine. |
| Synonym cycling | "The protagonist... the main character... the central figure..." | Pick one name and stick with it. |
| False ranges | "From X to Y" where X and Y aren't on a real scale | List the topics. Skip the range framing. |
Style patterns — the formatting tells:
| Pattern | What it looks like | The fix |
|---|---|---|
| Em dash overuse | Using em dashes everywhere for dramatic effect | Use commas, periods, or parentheses. |
| Excessive bold | Every other phrase in bold for emphasis | Bold sparingly or not at all. |
| Inline header lists | "**Speed:** The speed has improved..." | Write in prose. Skip the bold labels. |
| Title case headings | "Strategic Negotiations And Global Partnerships" | Sentence case: "Strategic negotiations" |
| Emoji decoration | Bullet points starting with emojis | Remove them unless the audience expects them. |
| Curly quotes | Using curly quotes instead of straight quotes | Use straight quotes in plain text. |
Communication patterns — the chatbot personality:
| Pattern | What it looks like | The fix |
|---|---|---|
| Chat artifacts | "I hope this helps!" "Let me know if..." "Certainly!" | Remove all chatbot pleasantries. |
| Cutoff disclaimers | "As of my last update..." "Based on available info..." | State facts directly, no disclaimers. |
| Sycophantic tone | "Great question!" "You're absolutely right!" | Skip the validation. Answer the question. |
| Filler phrases | "In order to" "Due to the fact that" "At this point in time" | "To" "Because" "Now" |
| Excessive hedging | "Could potentially possibly be argued that it might..." | Pick a position. |
| Generic conclusions | "The future looks bright" "Exciting times ahead" | End with a specific fact or next step. |
Same content, patterns gone ✂️
Example 1 — a blog intro. Before: "In today's rapidly evolving technological landscape, AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development." That's five AI tells in one sentence.
After: "AI coding assistants speed up some tasks, like writing simple functions. They help a lot less with debugging or big design decisions." Specific, plain, done. If you want a number in there, use a real one from a source you can name.
Example 2 — a product description. Before: "This groundbreaking tool boasts a vibrant interface, offering a seamless experience that fosters collaboration and enhances productivity. It's not just a tool, it's a catalyst for innovation." Promotional words plus a negative parallelism.
After: "The app has a shared workspace where your team can edit the same document at the same time. It saves about 2 hours per week compared to emailing files back and forth." What it actually does, with a specific number.
Advanced prompts 🎛️
Once the skill is installed, pair it with these. First — match a specific voice (yours):
/humanHere's an example of my writing style: [PASTE 2-3 PARAGRAPHS OF YOUR OWN WRITING]. Match this voice, sentence rhythm, and vocabulary level for everything you write in this chat.
Second — rewrite text that's already AI-written:
/humanRewrite the following text so it reads as 100% human-written. Remove every AI pattern. Keep the same information but change the sentence structures, word choices, and rhythm.[PASTE YOUR AI TEXT]
Third — the academic version, for essays and papers:
/humanWrite this in an academic tone but still avoid all AI patterns. Use formal language without the filler. Cite real sources properly and never invent one. No hedging, no sycophancy, no promotional language. Topic: [YOUR TOPIC]
And the one I run most — the self-audit. Use it on your own writing before anything important goes out:
Read the text below and identify every sign of AI writing. List each pattern you find with the specific phrase that triggered it. Then rewrite the text with all patterns removed.[PASTE TEXT TO AUDIT]
Links 🔗
- Wikipedia: Signs of AI writing— The full pattern list your skill is built from
- Claude— Skills work on every plan, including Free
- AI job search system— Pair the humanizer with your resume and cover letters
- The complete Claude guide— Everything else Claude can do
Liked this? Get the next one in your inbox.
Every Thursday I test new AI tools and send you the one worth using, with the exact steps and prompts. Plus the AI news that changes what you can do.