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

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/uu201/character-arc/humanizer-zh
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.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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 $0.00040 $0.01264
Sonnet 5 $0.00016 $0.00505
Haiku 4.5 $0.00008 $0.00253

Measured 5d ago against content hash 545ef3354937, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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. 5d 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 (549 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 2,527 once invoked, about $0.0004 per session on Opus 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.

Related

Other skills, from other repositories

omh-localization-review

This is a Hermes-native localization-review workflow skill.

rlaope/oh-my-hermes · 56 tokens

ppt-orchestrator

统一 PPT / 演示文稿 / 长图 / 周报 调度器。从ppt 出图法 V2 7 步,到 6 种风格字典(商务科技/博物图鉴/手绘科教/真实生活感/城市插画/反套路金句),到输出形式决策(HTML 阅读器 / 真实 .pptx / McKinsey HTML / huashu-design / design-master),下游分发到对应 skill 执行。Triggers:做 PPT / 做个演示 / 演示文稿 / 打包成 HTML / 真实 .pptx / 周报长图 / 卡脖子分析长图 / 幻灯片 / presentation / slides / deck。.

huangrichao2020/pretty-skills · 160 tokens

zhongguose-html-skill

以原稿章法为骨架,中国传统色彩为气韵,直接产出可交互、可迁移的中式 HTML 汇报演示稿。用于需要梳理叙事逻辑、章节框架、页级结构或版式的演示/汇报,且内容涉及中国文化,或视觉希望采用中国色、中国风、中式/东方审美;点名本 Skill、模板或框架导航格式时也触发。只支持 HTML 交付:输出 index.html + assets/ 目录(自包含、字体嵌入、可双击打开)。不生成 PPT/PPTX。 Build a Chinese-style HTML presentation system that maps confirmed source material into faithful reporting logic…

huangrichao2020/pretty-skills · 232 tokens

dashiai-ppt

制作 PPT、演示文稿、幻灯片、汇报材料时使用。DashiAI PPT 基于预置视觉主题组合页面,生成可离线打开、可在浏览器编辑的 HTML 演示,支持导出 PPTX / PDF 文件。.

huangrichao2020/pretty-skills · 62 tokens

wechat-delivery

公众号端到端交付——把任意选题在 30 分钟内变成可直接粘贴的桌面 8 文件交付物(标题/正文/封面/4 配图),用户手动 30 秒发布。适用场景:用户说"写公众号"/"公众号文章"/"配公众号"/"公众号配图"/自己的公众号名。覆盖 v3.18 launch 实战验证的 5 步流程 + 7 段黄金模板 + 桌面文件夹 + mavis browser 自动化天花板 + 反模式。.

huangrichao2020/pretty-skills · 129 tokens

教程类H5-小红书小工具

用 AI 生图 + SPA 课程架构 + 离线 H5 zip = 在小红书"创作者中心 → 小工具"发布的多课程 H5 互动产品。讲清楚 4 层栈 / 5 步流程 / 7 节课程都适用。触发词:「做教程类 H5」「小红书小工具」「H5 课程」「离线 H5 课程」「多节课 H5」。.

huangrichao2020/pretty-skills · 110 tokens