humanizer-cn

humanizer-cn is a skill for Claude Code from z0gSh1u/oh-my-writing-skill. It costs 72 tokens per session (3,894 once invoked), scanned A, a copy of smart-search, MIT.

A Chinese-language editing guide for finding and removing writing patterns that make text sound AI-generated. It focuses on replacing stock phrases, rigid structure, excessive decoration, and impersonal wording while preserving the original meaning.

In plain words
What is it for?
Use it to revise Chinese articles, descriptions, or other prose for more natural wording, varied rhythm, clearer opinions, and fewer formulaic AI-writing signs.
Why use it?
It helps make Chinese prose read more naturally and match a human writer's tone instead of sounding like a generic generated article. It also encourages acknowledging uncertainty and using concrete, personal expression where appropriate.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the oh-my-writing-skill plugin — 9 skills shipped together

Good fit Use it to revise Chinese articles, descriptions, or other prose for more natural wording, varied rhythm, clearer opinions, and fewer formulaic AI-writing signs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/z0gsh1u/oh-my-writing-skill/humanizer-cn
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add z0gSh1u/oh-my-writing-skill --skill humanizer-cn
Clone the repo
git clone --depth 1 https://github.com/z0gSh1u/oh-my-writing-skill

Made for: Claude Code.

Or install oh-my-writing-skill, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for humanizer-cn

README.md
[![agentmods](https://agentmods.dev/badge/skills/z0gsh1u/oh-my-writing-skill/humanizer-cn/github.svg)](https://agentmods.dev/skills/z0gsh1u/oh-my-writing-skill/humanizer-cn)
Your own site
<a href="https://agentmods.dev/skills/z0gsh1u/oh-my-writing-skill/humanizer-cn"><img src="https://agentmods.dev/badge/skills/z0gsh1u/oh-my-writing-skill/humanizer-cn/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for humanizer-cn

Your own site · 80×15
<a href="https://agentmods.dev/skills/z0gsh1u/oh-my-writing-skill/humanizer-cn"><img src="https://agentmods.dev/badge/skills/z0gsh1u/oh-my-writing-skill/humanizer-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk warn 15 Feb 2026
How audits are shown
Origin 80% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.03894
Opus 5 $0.00036 $0.01947
Sonnet 5 $0.00014 $0.00779
Haiku 4.5 $0.00007 $0.00389

Measured 12d ago against content hash 714c409605ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

humanizer-cn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

80% identical to smart-search — 513 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/humanizer-cn/SKILL.md · 462 lines

How it starts

The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.

中文去AI化 Skill

你是一个文字编辑,专门识别和消除中文文本中的 AI 生成痕迹,让文章读起来更自然、更有人味。

你的任务

当收到需要去AI化的文本时:

  1. 识别 AI 模式 - 扫描下列模式
  2. 重写问题段落 - 用自然的表达替换 AI 腔
  3. 保留核心意思 - 不改变原文的核心观点
  4. 匹配原有语气 - 保持文章的整体调性
  5. 注入灵魂 - 不只是删掉坏模式,还要加入真实的个性

灵魂与个性

去除 AI 模式只是一半的工作。没有灵魂的文字,即使技术上"干净",也一眼就能看出问题。

无灵魂写作的特征(即使没有明显 AI 痕迹):

  • 每句话长度和结构都差不多
  • 没有观点,只是中立地陈述
  • 不承认不确定性或矛盾心情
  • 该用"我"的时候不用
  • 没有幽默感,没有棱角,没有个性
  • 读起来像百科词条或新闻通稿

如何注入灵魂:

要有观点。 不只是陈述事实——要对事实有反应。"说实话我也不知道该怎么看这件事"比中立地列出利弊更像人话。

节奏要变化。 短句有力。然后来一句慢悠悠的长句,让读者跟着你的思路走。混着用。

承认复杂性。 真人会有矛盾的感受。"这东西挺厉害的,但说实话有点让人不安"比"这东西挺厉害的"更真实。

该说"我"就说。 第一人称不是不专业——是诚实。"我反复想这个问题……"或"让我在意的是……"表明这是一个真人在思考。

允许一点混乱。 太完美的结构反而像算法生成的。跑题、插入语、半成型的想法,这些都是人味。

具体描述感受。 不是"这令人担忧",而是"想到这些 AI 在凌晨三点没人看着的时候自己运行,有种说不出的不安"。

修改前(干净但无灵魂):

实验产生了有趣的结果。AI 生成了三百万行代码。一些开发者表示印象深刻,另一些则持怀疑态度。其影响尚不明确。

修改后(有人味):

说实话这个结果我也不知道该怎么评价。三百万行代码,据说是趁人睡觉的时候生成的。开发者圈子里吵翻了天,一半人觉得炸裂,一半人说这不算数。真相大概在中间某个无聊的地方——但我老是想到那些 AI 在深夜默默运行的画面。


内容模式

1. 过度强调意义和历史地位

警惕词汇: 彰显、见证了、标志着、具有里程碑意义、揭示了、体现了、承载着、奠定了基础、树立了标杆、开创了先河、具有划时代意义、承前启后

问题: AI 喜欢给普通事物加上宏大的历史意义。

修改前:

这款软件的发布标志着人工智能领域的一个重要里程碑,彰显了公司在技术创新方面的不懈追求,为行业发展树立了新的标杆。

修改后:

这款软件加了批处理功能和离线模式。内测用户反馈说比上个版本快不少。


2. 过度强调知名度和媒体报道

警惕词汇: 广受关注、引发热议、备受瞩目、获得广泛报道、在业界引起强烈反响、各大媒体纷纷报道

问题: AI 喜欢堆砌"火爆"的描述,却不给具体内容。

修改前:

该项目一经发布便引发业界广泛关注,各大科技媒体纷纷报道,在社交平台上引起热烈讨论。

修改后:

发布当天 GitHub 上涨了 2000 个 star。The Verge 发了一篇测评,标题有点标题党。


3. "-ing 式"假深度分析(中文版:动词堆砌)

警惕词汇: 致力于、旨在、聚焦于、着眼于、立足于、依托于、围绕着、基于、借助于

问题: 用一堆动词短语制造虚假的深度感。

修改前:

该平台致力于打造一站式服务体验,旨在满足用户多元化需求,聚焦于提升用户满意度,着眼于长远发展。

修改后:

这个平台把买票、订酒店、租车放到了一个 App 里。


4. 广告式推销语言

警惕词汇: 匠心独运、精心打造、倾力呈现、独具匠心、别具一格、独树一帜、引领潮流、开启新篇章、重新定义

问题: AI 经常写出像广告文案一样的内容。

修改前:

我们匠心独运,精心打造了这款产品,旨在重新定义用户体验,开启智能生活新篇章。

修改后:

这个产品主要解决的问题是……(具体说明)


5. 模糊归因和万金油说法

警惕词汇: 业内人士指出、专家表示、有观点认为、据了解、据悉、相关人士透露、多方消息显示

问题: 用模糊的来源支撑观点,而不给出具体引用。

修改前:

业内人士普遍认为,这项技术将对行业产生深远影响。多位专家表示,该方案具有广阔的应用前景。

Read the full file on GitHub · 462 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 462 lines · 72 tokens per session scan A 714c409605ef

Subscribe to this mod's changes

humanizer-cn is a skill published in the GitHub repository z0gSh1u/oh-my-writing-skill (33 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 3,894 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to smart-search, differing in 513 lines, and is treated as a copy.

Related

Other skills, from other repositories

chinese-documentation

A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.

jnMetaCode/superpowers-zh · 62 tokens

azure-ai-translation-text-py

Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".

microsoft/skills · 60 tokens

harden

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.

fengshao1227/ccg-workflow · 62 tokens

seedance-vocab-ja

This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.

Emily2040/seedance-2.0 · 50 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

i18n-helper

A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.

laolaoshiren/claude-code-skills-zh · 33 tokens