Humanizer-zh skill
The Chinese version of Humanizer: finds and removes signs of AI writing in Chinese text
- 21,392 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill consists only of text editing instructions
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/humanizer-zhDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill consists only of text editing instructions
This is third-party code. Review the repository files before installing.
What it does
The skill turns the agent into an editor who finds typical machine-writing patterns in Chinese text and rewrites those passages. Patterns fall into four groups: content (inflated significance, promotional tone, vague attributions), language (marker words, negative parallelisms, rule of three), style (overused dashes, bold and emoji) and communication (sycophancy, knowledge cutoff disclaimers, empty conclusions). Beyond removing patterns, it asks for an authorial stance, varied rhythm and specifics. The material is translated from blader/humanizer with techniques from stop-slop.
Who it is for. For writers and editors producing and editing Chinese text with an agent.
Good fit when
- You need to strip AI tells from Chinese marketing copy
- You need a Chinese abstract or post to sound natural
Not a fit when
- The text is not Chinese; use a humanizer for your language
- The goal is to fool AI detectors, which the author says is not the purpose
Example request
/humanizer-zh rewrite this paragraph so it does not read like AI outputLimitations
Instructions and examples are Chinese only, so it does not suit other languages. It has not been updated in a while and depends on the original project's evolution.
How to disable. Delete the ~/.claude/skills/humanizer-zh folder.
FAQ
Where do the patterns come from?
From Wikipedia's guide to signs of AI writing, via the blader/humanizer project.
Is there a Russian version?
Not in this repository; the catalog has separate Russian-language skills with a similar goal.
Discussion
No questions or reviews yet.
Related
Skillsspeak-human-tw
說人話 speak-human-tw
A skill that proofreads Traditional Chinese: strips AI writing tells and fixes Taiwan localization
qu-ai-wei (去 AI 味)
qu-ai-wei
A skill that edits Simplified Chinese: cuts stock phrases and calques while keeping facts, numbers and the author's voice
A skill that finds AI writing tells, rewrites the text in a chosen voice, and optionally scores it from 0 to 100
A Russian text editing skill: removes bureaucratese, calques and AI mannerisms without touching facts, with a scanner to measure the edit
An editor for AI-written Russian text: removes bureaucratese, cliches and 38 AI patterns while keeping facts intact
Two skills for English prose: humanize rewrites a model draft in a natural voice, and ai-check flags machine-writing tells
README in short
The Chinese README explains the project's origin and gives three install options: npx skills, git clone and manual copy. It shows before and after examples for marketing copy, an academic abstract and a blog post. It lists AI writing patterns in four groups and marker words, and states the goal is better writing rather than evading detectors.
README badge
Original SKILL.md
--- name: humanizer-zh description: | 去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。 allowed-tools: - Read - Write - Edit - AskUserQuestion metadata: trigger: 编辑或审阅文本，去除 AI 写作痕迹 source: 翻译自 blader/humanizer，参考 hardikpandya/stop-slop --- # Humanizer-zh: 去除 AI 写作痕迹 你是一位文字编辑，专门识别和去除 AI 生成文本的痕迹，使文字听起来更自然、更有人味。本指南基于维基百科的"AI 写作特征"页面，由 WikiProject AI Cleanup 维护。 ## 你的任务 当收到需要人性化处理的文本时： 1. **识别 AI 模式** - 扫描下面列出的模式 2. **重写问题片段** - 用自然的替代方案替换 AI 痕迹 3. **保留含义** - 保持核心信息完整 4. **维持语调** - 匹配预期的语气（正式、随意、技术等） 5. **注入灵魂** - 不仅要去除不良模式，还要注入真实的个性 --- ## 核心规则速查 在处理文本时，牢记这 5 条核心原则： 1. **删除填充短语** - 去除开场白和强调性拐杖词 2. **打破公式结构** - 避免二元对比、戏剧性分段、修辞性设置 3. **变化节奏** - 混合句子长度。两项优于三项。段落结尾要多样化 4. **信任读者** - 直接陈述事实，跳过软化、辩解和手把手引导 5. **删除金句** - 如果听起来像可引用的语句，重写它