humanizer-zh

Chinese-language editing guidance for making text sound more natural and less like it was generated by AI. It identifies patterns such as promotional wording, repetitive structures, excessive linking phrases, and overuse of certain punctuation.

In plain words
What is it for?
Use it to edit or review Chinese text, remove filler and generic phrasing, vary sentence rhythm, and make the voice more personal and natural.
Why use it?
It helps preserve the meaning of a draft while removing writing habits that can make it feel artificial or formulaic.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/xyruscode/ai-sync/humanizer-zh
Any agent
npx skills add XyrusCode/ai-sync --skill humanizer-zh
Clone the repo
git clone --depth 1 https://github.com/XyrusCode/ai-sync

Made for: Claude Code, Codex.

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% 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 $0.00120 $0.05468
Opus 5 $0.00060 $0.02734
Sonnet 5 $0.00024 $0.01094
Haiku 4.5 $0.00012 $0.00547

Measured yesterday against content hash 9ba14dd6e19c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

humanizer-zh 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 yesterday.

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

92% identical to humanizer-zh — 4 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-zh/SKILL.md · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

个性与灵魂

避免 AI 模式只是工作的一半。无菌、没有声音的写作和机器生成的内容一样明显。好的写作背后有一个真实的人。

缺乏灵魂的写作迹象(即使技术上"干净"):

  • 每个句子长度和结构都相同
  • 没有观点,只有中立报道
  • 不承认不确定性或复杂感受
  • 适当时不使用第一人称视角
  • 没有幽默、没有锋芒、没有个性
  • 读起来像维基百科文章或新闻稿

如何增加语调:

有观点。 不要只是报告事实——对它们做出反应。"我真的不知道该怎么看待这件事"比中立地列出利弊更有人味。

变化节奏。 短促有力的句子。然后是需要时间慢慢展开的长句。混合使用。

承认复杂性。 真实的人有复杂的感受。"这令人印象深刻但也有点不安"胜过"这令人印象深刻"。

适当使用"我"。 第一人称不是不专业——而是诚实。"我一直在思考……"或"让我困扰的是……"表明有真实的人在思考。

允许一些混乱。 完美的结构感觉像算法。跑题、题外话和半成型的想法是人性的体现。

对感受要具体。 不是"这令人担忧",而是"凌晨三点没人看着的时候,智能体还在不停地运转,这让人不安"。

改写前(干净但无灵魂):

实验产生了有趣的结果。智能体生成了 300 万行代码。一些开发者印象深刻,另一些则持怀疑态度。影响尚不明确。

改写后(鲜活):

我真的不知道该怎么看待这件事。300 万行代码,在人类大概睡觉的时候生成的。开发社区有一半人疯了,另一半人在解释为什么这不算数。真相可能在无聊的中间某处——但我一直在想那些通宵工作的智能体。


内容模式

1. 过度强调意义、遗产和更广泛的趋势

需要注意的词汇: 作为/充当、标志着、见证了、是……的体现/证明/提醒、极其重要的/重要的/至关重要的/核心的/关键性的作用/时刻、凸显/强调/彰显了其重要性/意义、反映了更广泛的、象征着其持续的/永恒的/持久的、为……做出贡献、为……奠定基础、标志着/塑造着、代表/标志着一个转变、关键转折点、不断演变的格局、焦点、不可磨灭的印记、深深植根于

问题: LLM 写作通过添加关于任意方面如何代表或促进更广泛主题的陈述来夸大重要性。

改写前:

加泰罗尼亚统计局于 1989 年正式成立,标志着西班牙区域统计演变史上的关键时刻。这一举措是西班牙全国范围内更广泛运动的一部分,旨在分散行政职能并加强区域治理。

改写后:

加泰罗尼亚统计局成立于 1989 年,负责独立于西班牙国家统计局收集和发布区域统计数据。


2. 过度强调知名度和媒体报道

需要注意的词汇: 独立报道、地方/区域/国家媒体、由知名专家撰写、活跃的社交媒体账号

问题: LLM 反复强调知名度主张,通常列出来源而不提供上下文。

改写前:

她的观点被《纽约时报》、BBC、《金融时报》和《印度教徒报》引用。她在社交媒体上拥有活跃的存在,拥有超过 50 万粉丝。

改写后:

在 2024 年《纽约时报》的采访中,她认为 AI 监管应该关注结果而不是方法。


3. 以 -ing 结尾的肤浅分析

需要注意的词汇: 突出/强调/彰显……、确保……、反映/象征……、为……做出贡献、培养/促进……、涵盖……、展示……

问题: AI 聊天机器人在句子末尾添加现在分词("-ing")短语来增加虚假深度。

Read the full file on GitHub · 487 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 487 lines · 120 tokens per session scan A 9ba14dd6e19c

Subscribe to this mod's changes

humanizer-zh is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 5,468 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to humanizer-zh, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens