Editorial illustration for Wiki Guide to Spot AI Writing Powers New Claude Code ‘Humanize’ Plug‑In
AI Writing Tells: Wikipedia's Guide to Spotting Bots
Wiki Guide to Spot AI Writing Powers New Claude Code ‘Humanize’ Plug‑In
The Wikipedia guide for spotting AI-generated text was never meant to be a blueprint for faking humanity. Yet here we are. A new “skill file” for Anthropic’s Claude Code, built by developer Chen, takes the very patterns the guide warns us about and weaponizes them in reverse.
It instructs the model to drop the sterile cadence, embrace imperfection, and sound like a person who actually hesitates. The result is a plug-in that tries to humanize the chatbot by leaning into the hallmarks of organic writing: opinions, uncertainty, casual phrasing. But there’s a catch.
The same instructions that make prose feel less robotic can also undermine its precision, especially for technical tasks. And the irony isn’t lost: the most referenced rulebook for sniffing out AI help may now help some people hide it.
On Saturday, tech entrepreneur Siqi Chen released an open source plug-in for Anthropic’s Claude Code AI assistant that instructs the AI model to stop writing like an AI model.
The irony cuts deep. A guide built to spot machine-made text now becomes the very blueprint for making it disappear. Chen’s skill file doesn’t solve the deeper problem, it papers it over with conversational ticks, manufactured doubt, and the illusion of a personality.
But that may be enough. In a world where readers are trained to sniff out robotic fluency, a little calculated imperfection can go a long way. The real question isn’t whether the Humanizer works.
It’s whether we’ll keep playing this game of digital hide‑and‑seek, or finally ask ourselves why we need to hide at all.
Related Reading
Browse all Anthropic news →
AI Tools & Apps Claude gains shared context in Excel, PowerPoint; Microsoft adds Copilot Cowork
AI Tools & Apps Windows Copilot AI unable to pinpoint image source in user test
AI Tools & Apps LG's recent webOS update adds Microsoft Copilot app, now removable
Related Topic Anthropic says Claude writes >90% of its code; AI pause button urged
LLMs & Generative AI
Related Topic Claude Mythos highlights EU AI safety gaps, says researcher Caroli
Policy & Regulation
 [](https://cms.aidailypost.com/uploads/90_salesforce_engineers_use_cursor_daily_saying_it_filled_senior_gaps_0ad7110c48.webp "Salesforce engineers use Cursor daily, filling senior gaps. [nngroup.com](https://www.nngroup.com/articles/write-alt-text/) [")
From Archives 90% of Salesforce engineers use Cursor daily, saying it filled senior gaps
From Archives Oxford colleges gain secure access to Google's Gemini 3 AI model
From Archives Anthropic unveils Claude constitution urging builders to ensure safety
LLMs & Generative AI
From Archives Anthropic CEO warns AI chip exports to China pose national security risk
Business & Startups
Common Questions Answered
How does the new Claude Code 'Humanize' plug-in help developers avoid AI-generated writing patterns?
The plug-in provides a curated list of 24 linguistic quirks that help identify and avoid AI-generated text patterns. By appending these instructions to the model's prompt, the skill file steers Claude Code away from typical AI phrasing, making the writing sound more natural and human-like.
What makes the Wikipedia guide to spotting AI writing unique for developers?
The Wikipedia guide offers a detailed field guide of writing conventions typical of AI chatbots, with real examples taken from various sources. It transforms a defensive tool for detecting AI-generated content into a constructive approach for improving AI-generated writing by highlighting specific patterns to avoid.
How did Siqi Chen contribute to improving AI writing through the Claude Code skill file?
Chen created a skill file that was posted on GitHub and quickly gained over 1,600 stars. The file is a simple Markdown document that provides specific instructions to Claude Code about avoiding AI-generated writing patterns, operating at the prompt level to make the assistant's output sound more authentically human.
Further Reading
- The best guide to spotting AI writing comes from Wikipedia — TechCrunch
- Wikipedia's Guide to Spotting AI Is Now Being Used To Hide AI — Slashdot
- Wikipedia Cracks the Code on Spotting AI Writing — The Tech Buzz
- Wikipedia Launches Guide to Spotting AI-Generated Content — Article Factory
