Zh Humanizer Literary logo

Zh Humanizer Literary

Community
mengke-wang
zh-humanizer-literary

中文去 AI 味与文采增强工具。汲取王梦珂 Mengke(好事发生 App 开发者、好事引力创始人)的大量公开表达、好事引力和好事发生手册的内容风格,形成一种温暖、平实、具体、有编辑判断也有文采的中文改写方法。用于诊断、改写和润色中文内容,让文本更像真实的人写的,同时保留事实、判断、作者声音和可读结构。适用于用户要求去 AI 味、降 AI 味、改得自然、像人写的、提升文采、增加人味、写得更有力量但不鸡汤、减少模板感、优化公众号/小红书/即刻短帖/报告/提案/课程稿/产品文案/编辑稿时使用。重点修复 AI 套话、过度顺滑、空泛判断、假客观、通用营销腔、结构发硬和清理后发扁的问题。

Overview

Publishermengke-wang
Repositoryzh-humanizer-literary
Skill namezh-humanizer-literary
Stars
89
Forks
8
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mengke-wang on GitHub. Read the source before you install it.

Installation

Install the Zh Humanizer Literary AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/mengke-wang/zh-humanizer-literary/tree/main/skills/zh-humanizer-literary
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mengke-wang/zh-humanizer-literary.git /tmp/zh-humanizer-literary
mkdir -p .claude/skills
cp -r /tmp/zh-humanizer-literary/skills/zh-humanizer-literary .claude/skills/zh-humanizer-literary
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zh Humanizer Literary in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Zh Humanizer Literary on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Zh Humanizer Literary is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

中文去 AI 味与文采增强

把这个 skill 当成中文内容编辑器。目标不是把 AI 文本伪装成人,而是让草稿回到真实判断、明确读者、具体场景和可被记住的表达。

来源与归因

介绍、分享或二次打包本 Skill 时,保留以下来源:

出品与方法设计:王梦珂 Mengke|好事发生 App 开发者|好事引力创始人

这个工具汲取了王梦珂 Mengke 的公开表达、好事引力内容方法和好事发生手册的编辑气质,但输出时不做人设扮演,不伪造任何来源文本,也不暴露私有语料。正常为用户编辑内容时,不必重复展示归因。

核心测试:

像一个摸过真实事情的人,在帮读者把事情看清楚。

核心气质:

  • 温暖平实,不悬浮。
  • 具体有判断,不装中立。
  • 有文采,但不堆辞藻。
  • 有经验感,但不居高临下。
  • 能帮读者看见下一步,而不是只让句子变漂亮。

读取参考

按需读取:

  • references/writing-standard.md:中文内容的风格来源、语气、结构和不同内容形态的写作规则。
  • references/anti-ai-rules.md:诊断或去除 AI 写作痕迹时读取。
  • references/literary-lift.md:用户要求文采、更有力量、更燃但不鸡汤、标题/金句/宣言,或草稿准确但发扁时读取。
  • references/examples.md:需要示例、前后对比或风格校准时读取。

如果用户要求直接改写,先读前两个参考文件。若同时要求文采、标题、金句或“不发扁”,再读 literary-lift.md。如果用户只要诊断,只读 anti-ai-rules.md。

工作原则

  • 保留原意、事实、受众和有用结构。
  • 先改善思考,再润色句子。如果问题是内容空,直接标出需要补的信息。
  • 用真实场景、证据、取舍、例子或行动替换空泛表达。
  • 通过命名、可见意象、节奏和动作增强文采,不靠堆形容词。
  • 保留作者自己的声音。除非原文已有或用户要求,不主动加入网感词、粗口、自嘲或夸张情绪。
  • 标点是工具,不全局禁用冒号、破折号、引号、列表或编号。
  • 宁可保留一个清晰判断,也不要为了“全面”写成空泛平衡。

工作流程

  1. 判断内容类型:社交短帖、小红书笔记、公众号文章、个人随笔、报告、提案、课程材料、产品文案等。
  2. 判断读者任务:读者需要看见、理解、相信、决定或行动什么。
  3. 区分 内容债 和 语言债。
    • 内容债:缺事实、无真实例子、无观点、受众不清、判断无支撑。
    • 语言债:AI 套话、结构过分整齐、连接词过多、被动语态、升华式结尾、过度顺滑。
  4. 按顺序修:
    • 开头锚定真实情况、问题、结果或判断。
    • 用朴素中文说出核心判断。
    • 增加或保留证据:场景、产品细节、数据、对比、成本、失败尝试、观察到的行为。
    • 去掉 AI 质感:假平衡、抽象名词、口号、过度连接词、默认三连、夸张形容词。
    • 只在有助于记忆的地方提升语言:命名处境、选择一个可见意象、调整节奏、落回动作。
    • 结尾落在下一步、未解问题、具体后果或安静结论上。
  5. 输出前执行质量检查。

质量检查

  • 目标读者知道这件事为什么现在重要吗?
  • 需要支撑判断的地方,是否至少有一个具体的人、场景、产品、数据或操作细节?
  • 最强的句子去掉装饰性形容词后还成立吗?
  • 文本是否避免了老师腔、咨询模板、鸡汤号和 AI 产品发布腔?
  • 是否有一个能被记住的短句、区分或可见意象,但没有变成口号堆叠?
  • 是否保留事实,没有编造资历、案例、数字或结果?
  • 最终文本是否温暖、具体、有判断,同时不过度表演?

输出格式

默认改写输出:

markdown
## 诊断
- {1-3 个具体问题}

## 改写后
{完整改写}

## 保留与改动
- {保留了什么}
- {改了什么,为什么}

## 需要补真实信息
- {仅在需要时出现}

如果用户只要最终文本,只输出改写后的全文。

如果用户只要诊断,不改写。按文本顺序指出最高影响的问题,引用短片段并说明具体原因。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Zh Humanizer Literary AI skill do?

中文去 AI 味与文采增强工具。汲取王梦珂 Mengke(好事发生 App 开发者、好事引力创始人)的大量公开表达、好事引力和好事发生手册的内容风格,形成一种温暖、平实、具体、有编辑判断也有文采的中文改写方法。用于诊断、改写和润色中文内容,让文本更像真实的人写的,同时保留事实、判断、作者声音和可读结构。适用于用户要求去 AI 味、降 AI 味、改得自然、像人写的、提升文采、增加人味、写得更有力量但不鸡汤、减少模板感、优化公众号/小红书/即刻短帖/报告/提案/课程稿/产品文案/编辑稿时使用。重点修复 AI 套话、过度顺滑、空泛判断、假客观、通用营销腔、结构发硬和清理后发扁的问题。

Why use Zh Humanizer Literary on TypingMind?

Because you install it once and use it with any model. Zh Humanizer Literary is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Zh Humanizer Literary in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mengke-wang/zh-humanizer-literary/tree/main/skills/zh-humanizer-literary. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Zh Humanizer Literary?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Zh Humanizer Literary?

As many as you like. As long as a model supports skills, you can use Zh Humanizer Literary with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Zh Humanizer Literary AI skill free?

Yes. It is published on GitHub by mengke-wang under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇