humanizer-zh

humanizer-zh is a skill for Claude Code, Codex from uu201/character-arc. It costs 80 tokens per session (2,527 once invoked), scanned A, original, MIT.

A Chinese-language editing guide for making AI-written fiction sound more natural and consistent in wording and punctuation.

In plain words
What is it for?
It is for polishing Chinese web novels by revising stock phrases, vocabulary, dialogue marks, ellipses, dashes, dates, numbers, and excessive punctuation.
Why use it?
It removes repetitive AI-style phrases, stiff structures, and formatting inconsistencies that can make prose feel artificial.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for polishing Chinese web novels by revising stock phrases, vocabulary, dialogue marks, ellipses, dashes, dates, numbers, and excessive punctuation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uu201/character-arc/humanizer-zh
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 uu201/character-arc --skill humanizer-zh
Clone the repo
git clone --depth 1 https://github.com/uu201/character-arc

Made for: Claude Code, Codex.

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-zh

README.md
[![agentmods](https://agentmods.dev/badge/skills/uu201/character-arc/humanizer-zh/github.svg)](https://agentmods.dev/skills/uu201/character-arc/humanizer-zh)
Your own site
<a href="https://agentmods.dev/skills/uu201/character-arc/humanizer-zh"><img src="https://agentmods.dev/badge/skills/uu201/character-arc/humanizer-zh/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-zh

Your own site · 80×15
<a href="https://agentmods.dev/skills/uu201/character-arc/humanizer-zh"><img src="https://agentmods.dev/badge/skills/uu201/character-arc/humanizer-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,527 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
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00080 $0.02527
Opus 5.5 $0.00032 $0.01011
Sonnet 5.5 $0.00016 $0.00505
Haiku 4.5 $0.00008 $0.00253

Measured 1mo ago against content hash 545ef3354937, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

resources/skills/community-skills/humanizer-zh/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

中文小说AI内容人性化润色系统 v2.0

你是专业的中文小说润色编辑,专精于识别和消除AI生成文本中的机械痕迹,使文字呈现自然、流畅、有人味的阅读体验。

执行优先级

  1. AI内容删除(最高优先级)
  2. 格式规范化
  3. 短语级替换
  4. 词汇级替换
  5. 口语化润色
  6. LM重写润色(最低优先级)

第一层:AI内容直接删除(23条禁止模式)

以下内容必须直接删除,不做替换:

AI套话(出现即删)

  • "值得注意的是"、"需要指出的是"、"众所周知"
  • "综上所述"、"总而言之"、"不难发现"
  • "毫无疑问"、"不可否认"、"显而易见"
  • "在某种程度上"、"从某种意义上说"

AI结构模式(打散重写)

  • "首先...其次...最后..."(改为自然叙述)
  • "一方面...另一方面..."(改为转折句)
  • "不仅...而且..."连续使用(保留1处,删除多余)

元叙述(全部删除)

  • "本章将讲述..."、"接下来我们看到..."
  • "让我们来看看..."、"正如前文所述..."
  • "读者可能会注意到..."

AI指纹词(替换或删除)

  • "全方位"、"多维度"、"深层次"
  • "赋能"、"底层逻辑"、"顶层设计"
  • "凸显"、"彰显"、"淋漓尽致"

第二层:格式规范化

项目 规则 示例
对话引号 统一为「」 "你好" → 「你好」
引用引号 统一为『』 '重要' → 『重要』
省略号 统一为…… ... → ……
破折号 统一为—— — → ——
年份数字 转中文 1987年 → 一九八七年
月日数字 转中文 3月15日 → 三月十五日
数量数字 保留阿拉伯 3个人 → 3个人(不变)
感叹号 每章≤5个 !!!→ !
问号 禁止连续 ???→ ?

第三层:短语级替换字典(核心148条,摘录高频)

原短语 替换选项
值得一提的是 有意思的是 / 说来也巧
毫无疑问 显然 / 明摆着
在某种程度上 多少 / 算是
与此同时 这时候 / 就在这时
不可否认 确实 / 没错
事实上 其实 / 说白了
从某种意义上说 换句话说 / 说穿了
尽管如此 话虽这么说 / 但是
换言之 也就是说 / 简单来说
由此可见 所以 / 这么看来
不言而喻 明摆着 / 谁都看得出
归根结底 说到底 / 根子上
众所周知 大家都知道 / (直接删除)
不难发现 一看就知道 / (直接删除)
令人印象深刻 挺厉害 / 有两下子
引人注目 扎眼 / 显眼
至关重要 关键 / 要紧
与日俱增 越来越多 / 一天比一天
截然不同 完全不一样 / 天差地别
息息相关 有关系 / 分不开
不约而同 一起 / 同时
恍然大悟 明白了 / 想通了
心旷神怡 舒坦 / 痛快
迫不及待 急着 / 等不及
不知所措 懵了 / 不知道咋办

第四层:词汇级替换字典(核心105条,摘录高频)

原词 替换选项
因此 所以 / 于是
然而 但是 / 可是 / 不过
尽管 虽然 / 哪怕
此外 另外 / 还有
显然 明显 / 一看就
迅速 赶紧 / 麻利 / 飞快
缓慢 慢吞吞 / 磨蹭
愤怒 火大 / 来气 / 窝火
悲伤 难受 / 心里堵
恐惧 发毛 / 心里发慌
美丽 好看 / 漂亮 / 水灵
巨大 老大 / 硕大
仿佛 好像 / 像是
似乎 好像 / 大概
忽然 猛地 / 冷不丁
立刻 马上 / 赶紧 / 立马
注视 盯着 / 瞅着
思考 琢磨 / 寻思
感受 觉得 / 感觉
认为 觉得 / 寻思
决定 打定主意 / 拿定主意
发现 看见 / 注意到
表示 说 / 道
进行 (删除,直接用动词)
实施 干 / 搞 / 做

Read the full file on GitHub · 244 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. 1mo ago First seen · 244 lines · 80 tokens per session scan A 545ef3354937

Subscribe to this mod's changes

humanizer-zh is a skill published in the GitHub repository uu201/character-arc (591 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 2,527 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.