风格库再大，也装不下所有人的偏好。有人想写成半佛仙人，有人想写成和菜头，还有人想照着昨天看到的一篇没听过名字的作者的文章来。怎么办？让 AI 现场提取风格 DNA——给一篇范文，改成那个味。

A style library, no matter how large, can't cover everyone's taste. Some users want to write like an author who isn't in the library. Some want the voice of one specific article, not a generalized style. The solution: real-time style extraction. Give the AI any reference article, and it clones the writing DNA on the fly.

一套写作指南搞定了翻译腔，但科技评测文章写成半佛那味儿就离谱了。不同内容需要不同声音。我研究了怎么从任何一个作者身上'偷'写作风格——收集文章、拆解模式、提炼成结构化的 Style Profile。这篇用卡兹克做例子，走一遍完整流程。

One style guide fixed translation-ese, but a tech review shouldn't sound like social commentary. Different content needs different voices. I developed a systematic method for 'stealing' any author's writing style — collecting articles, dissecting patterns, and extracting a structured Style Profile. Here's the full process, demonstrated with a real example.

我博客上 83 篇中文文章，每篇都读着像英文翻译过来的。翻译腔、长段落、学术味——全是 AI 写作的通病。我研究了半佛仙人、九边、虎嗅的写作方法论，提炼出一份 435 行的写作系统，喂给 Claude，把 83 篇全部重写了。这是那份指南的故事。

My blog had 83 Chinese posts — all of them read like translated English. Stiff, formal, academic. So I studied China's best WeChat writers, distilled their craft into a 435-line writing system, and fed it to Claude as a system prompt. Then I rewrote every single post. This is the story of that guide.

有读者说我们的中文文章'用语很生硬'。我一看——确实，全是翻译腔。英文思维，中文外壳。于是我花了一周研究公众号爆款怎么写的，搞了 435 行写作指南，把整个中文写作管线推翻重建。这是那个过程的记录。

Our Chinese blog articles read like translated English — stiff, academic, lifeless. A reader noticed. We spent a week researching what makes Chinese 公众号 articles work, built a 435-line style guide, and rebuilt the entire writing pipeline. Here's what we learned about the gap between 'correct Chinese' and 'native Chinese.'