Humanizer Zh logo

Humanizer Zh

Community
843645440
humanizer-zh

去除中文文本中的 AI 生成痕迹,保留事实、原意和所需语气。用于编辑或审阅文本,使句子更直接、节奏更自然、归因更具体,并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留;不用于虚构经历、事实或情绪。

Overview

Publisher843645440
Repositorywechat-skill
Skill namehumanizer-zh
Stars
132
Forks
29
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by 843645440 on GitHub. Read the source before you install it.

Installation

Install the Humanizer Zh 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/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh
  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/843645440/wechat-skill.git /tmp/wechat-skill
mkdir -p .claude/skills
cp -r /tmp/wechat-skill/.agents/skills/humanizer-zh .claude/skills/humanizer-zh
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Humanizer Zh 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 Humanizer Zh 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 Humanizer Zh 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.

Humanizer-zh

把文本改得像一个具体的人写的,而不是简单换同义词。目标是更直接、更有节奏、更符合原定声口,同时不扩张事实。

不可越过的边界

  • 不新增数字、人物、引语、案例、来源、现场细节、亲历、采访、动机或结论。
  • 不把不确定内容改成确定事实,不删除原文中的必要限定和来源边界。
  • 不擅自改变立场、受众、文体和风险级别;正式报道不能被改成情绪化自媒体文。
  • 保留标题层级、链接、引用、代码、表格和用户要求保留的结构。
  • 若原文缺少支撑,不用“更具体”的虚构细节填空;改为删掉空泛主张或明确其不确定性。

先确定声口

按 brief 或原文选择,不把“人味”误解为一律使用第一人称:

模式目标
正式报道 / 公共事件档案克制、清楚、事实优先;情绪来自事实后果,不注入“我很愤怒”等表演性反应
观点 / 行业专栏可保留第一人称和锋利判断;情绪必须钉在已知机制、成本或责任上
教程 / 技术说明直接、准确、少铺垫;不强行加个性段落
普通编辑匹配原文语气,只清理机器痕迹

一轮改写法

  1. 锁定事实:先标出数字、日期、专名、引语、来源、结论状态和必要限定,改写后逐项核对。
  2. 删除空话:删“值得注意的是”“标志着重要转折”“不断演变的格局”等不增加信息的句子。
  3. 修正归因:有明确来源就写来源;没有就删掉“专家认为”“多方指出”之类假权威,不自造出处。
  4. 拆公式结构:处理“不仅……而且……”“不是……而是……”、机械三段式、每节同构和“挑战与展望”模板。
  5. 恢复自然节奏:长短句交错,能用“是/有/可以”就不用绕弯结构;允许关键词自然重复,不做同义词循环。
  6. 清理展示痕迹:删聊天式开场、免责声明、讨好语、emoji、过多粗体、内联小标题列表和万能积极结尾。
  7. 终检:朗读一遍,检查事实未膨胀、立场未漂移、语气符合模式、段落不再像同一模板复制。

优先处理最影响阅读的句子,不为追求“变化”把每句话都改一遍。空洞金句应删;有事实或机制支撑的锋利判断可以保留。

快速检查

  • 连续三句长度和结构相同:拆掉其中一句或合并两句。
  • 一段里出现多个“此外、然而、同时、值得注意的是”:多数可直接删除。
  • “从 A 到 B”不是同一尺度、“三项”只是为了凑完整:改为真实关系和真实数量。
  • 破折号、括号、粗体和冒号列表抢过正文:减少展示性标记。
  • 段尾总是口号、反问或一句金句:改成事实、代价、未决边界,或直接结束。
  • 读起来很顺却没有任何可核验信息:删除或回到来源补证,不润色成更像真的话。

24 类模式及其最短修法见 references/pattern-catalog.md。只有文本顽固、需要解释修改原因或做专项审阅时才加载,不是每次必读。

输出

默认只给改写后的完整文本。用户要求审阅说明时,再附一段简短修改摘要;不要输出内部评分表或逐句思考过程。

在微信公众号流水线中

被 wechat-content-pipeline 调用时:

  1. 读取 references/wechat-pipeline-constraints.md 和流水线的 references/humanize-pass.md。
  2. 只就地改写任务目录里的 article.md 一轮,不修改其他产物,不把说明写进正文。
  3. 保持唯一一级标题、必要二级标题与 Markdown 结构,纯正文字数仍须在 2500—5000。
  4. user-brief.md 标有“公共事件档案模式”时使用克制报道声口;其他稿件按 brief 和账号档案决定是否使用强情感第一人称。
  5. 保留 dossier 的结论状态、时间线、来源边界和隐私处理;禁止用修辞强化未被来源支持的指控。

本 Skill 源自 op7418/Humanizer-zh,其上游参考 Wikipedia 的 “Signs of AI writing”。本仓库版本为公众号流水线加入了事实、声口和公共事件约束;同步上游时不得覆盖这些边界。

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 Humanizer Zh AI skill do?

去除中文文本中的 AI 生成痕迹,保留事实、原意和所需语气。用于编辑或审阅文本,使句子更直接、节奏更自然、归因更具体,并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留;不用于虚构经历、事实或情绪。

Why use Humanizer Zh on TypingMind?

Because you install it once and use it with any model. Humanizer Zh 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 Humanizer Zh in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh. 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 Humanizer Zh?

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 Humanizer Zh?

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

Is the Humanizer Zh AI skill free?

It is published on GitHub by 843645440. Check the repository for licensing terms. 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 👇