Wikipedia's AI detection guide becomes blueprint for tool that makes chatbots sound more human

A Wikipedia Group Made a Guide to Detect AI Writing. Now a Plug-In Uses It to 'Humanize' Chatbots

The web's best resource for spotting AI writing has ironically become a manual for AI models to 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. Called Humanizer, the simple prompt plug-in feeds Claude a list of 24 language and formatting patterns that Wikipedia editors have listed as chatbot giveaways. Chen published the plug-in on GitHub, where it has picked up more than 1,600 stars as of Monday. "It's really handy that Wikipedia went and collated a detailed list of 'signs of AI writing,'" Chen wrote on X. "So much so that you can just tell your LLM to ... not do that." The source material is a guide from WikiProject AI Cleanup, a group of Wikipedia editors who have been hunting AI-generated articles since late 2023. French Wikipedia editor Ilyas Lebleu founded the project. The volunteers have tagged over 500 articles for review and, in August 2025, published a formal list of the patterns they kept seeing. Chen's tool is a "skill file" for Claude Code, Anthropic's terminal-based coding assistant, which involves a Markdown-formatted file that adds a list of written instructions (you can see them here) appended to the prompt fed into the large language model that powers the assistant. Unlike a normal system prompt, for example, the skill information is formatted in a standardized way that Claude models are fine-tuned to interpret with more precision than a plain system prompt. (Custom skills require a paid Claude subscription with code execution turned on.) But as with all AI prompts, language models don't always perfectly follow skill files, so does the Humanizer actually work? In our limited testing, Chen's skill file made the AI agent's output sound less precise and more casual, but it could have some drawbacks: It won't improve factuality and might harm coding ability. In particular, some of Humanizer's instructions might lead you astray, depending on the task. For example, the Humanizer skill includes this line: "Have opinions. Don't just report facts -- react to them. 'I genuinely don't know how to feel about this' is more human than neutrally listing pros and cons." While being imperfect seems human, this kind of advice would probably not do you any favors if you were using Claude to write technical documentation. Even with its drawbacks, it's ironic that one of the web's most referenced rule sets for detecting AI-assisted writing may help some people subvert it. Spotting the Patterns So what does AI writing look like? The Wikipedia guide is specific with many examples, but we'll give you just one here for brevity's sake. Some chatbots love to pump up their subjects with phrases like "marking a pivotal moment" or "stands as a testament to," according to the guide. They write like tourism brochures, calling views "breathtaking" and describing towns as "nestled within" scenic regions. They tack "-ing" phrases onto the end of sentences to sound analytical: "symbolizing the region's commitment to innovation." To work around those rules, the Humanizer skill tells Claude to replace inflated language with plain facts and offers this example transformation: Before: "The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain." After: "The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics." Claude will read that and do its best as a pattern-matching machine to create an output that matches the context of the conversation or task at hand. Why AI Writing Detection Fails Even with such a confident set of rules crafted by Wikipedia editors, we've previously written about why AI writing detectors don't work reliably: There is nothing inherently unique about human writing that reliably differentiates it from LLM writing. One reason is that even though most AI language models tend toward certain types of language, they can also be prompted to avoid them, as with the Humanizer skill. (Although sometimes it's very difficult, as OpenAI found in its yearslong struggle against the em dash.)

This plugin uses Wikipedia's AI-spotting guide to make AI writing sound more human

A new tool aims to help AI chatbots generate more human-sounding text -- with the help of Wikipedia's guide for detecting AI, as reported by Ars Technica. Developer Siqi Chen says he created the tool, called Humanizer, by feeding Anthropic's Claude the list of tells that Wikipedia's volunteer editors put together as part of an initiative to combat "poorly written AI-generated content." Wikipedia's guide contains a list of signs that text may be AI-generated, including vague attributions, promotional language like describing something as "breathtaking," and collaborative phrases, such as "I hope this helps!" Humanizer, which is a custom skill for Claude Code, is supposed to help the AI assistant avoid detection by removing these "signs of AI-generated writing from text, making it sound more natural and human," according to its GitHub page. The GitHub page provides some examples on how Humanizer might help Claude detect some of these tells, including by changing a sentence that described a location as "nestled within the breathtaking region" to "a town in the Gonder region," as well as adjusting a vague attribution, like "Experts believe it plays a crucial role" to "according to a 2019 survey by..." Chen says the tool will "automatically push updates" when Wikipedia's AI-detecting guide is updated. It's only a matter of time before the AI companies themselves start adjusting their chatbots against some of these tells, too, as OpenAI has already addressed ChatGPT's overuse of em dashes, which has become an indicator of AI content.