Zh Tech Writing logo

Zh Tech Writing

Community
leter
zh-tech-writing

中文技术文档写作规范。写或修改中文技术文档、开发文档(README、设计文档、接口说明、教程)时使用。

Overview

Publisherleter
Repositoryzh-tech-writing
Skill namezh-tech-writing
Stars
385
Forks
20
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Zh Tech Writing 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/leter/zh-tech-writing/tree/main/skills/zh-tech-writing
  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/leter/zh-tech-writing.git /tmp/zh-tech-writing
mkdir -p .claude/skills
cp -r /tmp/zh-tech-writing/skills/zh-tech-writing .claude/skills/zh-tech-writing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zh Tech Writing 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 Tech Writing 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 Tech Writing 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.

中文技术文档写作

目标:写出像资深工程师写的中文技术文档。平实、具体、短句。

流程

写新文档:

  1. 先想清楚读者是谁,读完要能做成什么事。一句话说不清,先问用户。
  2. 按下面的“句子”“语气”“段落与结构”“排版”写。
  3. 自检:拿“AI 腔清单”逐条对照全文,命中的全部改掉。
  4. 跑 autocorrect --fix <文件>,修空格和标点。命令不存在就跳过,改为按“排版”手动检查。
  5. 手动检查 autocorrect 管不到的:引号、省略号、破折号。

修改已有文档:

  1. 通读全文,再动手。
  2. 用户只要意见:按“原句 → 改后 → 原因”列出问题,不改文件。
  3. 否则直接改,然后做上面的第 3~5 步。最后用两三句话说明改了哪几类问题。

每一步都做完才算完成。第 3 步的标准是:清单每一条都对照过,全文没有命中。

句子

  • 用逗号隔开的每一截,尽量在 20 字以内。超过 30 字就拆开。整句不超过 100 字。
  • 一句只说一个意思。多用简单句和并列句,把长定语拆出去。
    • 差:那个昨天生病的人没有参加会议。
    • 好:他昨天生病了,没有参加会议。
  • 用肯定句,不用双重否定。
    • 差:请确认没有接通装置的电源。 → 好:请确认装置的电源已关闭。
    • 差:没有删除权限的用户,不能删除此文件。 → 好:用户必须有删除权限,才能删除此文件。
  • 用主动语态,少用“被”。
    • 差:假如此软件尚未被安装 → 好:假如还没安装这个软件
  • 动词直接用,不套“进行”“做出”。
    • 差:对配置文件进行修改 → 好:修改配置文件
  • “这”“其”“该”只指一个明确的对象。可能有歧义就把名词重复一遍。
  • 名词前的修饰语不超过两层,多了就拆成两句。
  • 用现代汉语常用词,不用文言、生造词。
    • 差:这是唯二的方法。 → 好:只有这两种方法。
  • 分清“的、地、得”:开心的笑容、开心地笑、笑得开心。

语气

  • 像给同事讲清楚一件事:口语化可以,网络流行语不用。
  • 称呼读者用“你”,称呼项目方用“我们”。
  • 用陈述语气,句末用句号。
  • 用事实代替形容词:给出数字、命令、文件名、报错原文。
    • 差:性能得到了大幅提升。
    • 好:p99 延迟从 120 ms 降到 40 ms。
  • 确定的事直接说。不确定就说清楚哪里不确定、怎么验证。

段落与结构

  • 每段第一句说这段的重点,后面的句子为它服务。一段一个主题。
  • 一段最好不超过 4 行,最多 7 行。
  • 标题用二级、三级为主:
    • 一级标题下直接接二级,不跳级。
    • 同级标题只有一个时,去掉这层标题。
    • 下级标题不重复上级标题的名字。
    • 需要四级标题时,改用 **(1)xxx** 或列表。
    • 标题末尾不加句号、逗号、冒号。
  • 列表只放真正并列、可以单独扫读的条目。有因果、转折关系的内容,写成段落。
  • 加粗只给读者必须注意的警告或关键词,一屏最多一两处。
  • 引用别人的内容或图片,注明出处。

排版

每篇都要守的规则:

  • 中文与英文、数字之间加一个半角空格:在 Linux 上安装 5 个包。
  • 中文句子用全角标点:,。:;?()。整句是英文时用半角标点。
  • 英文、数字后面紧跟全角标点时,中间不加空格:他用的是 MacBook Air。
  • 引号用全角 “ ”,引号里再套引号用 ‘ ’。
  • 并列的词用顿号 、 隔开,最后一项用“和”连接:Google、腾讯和百度。
  • 省略号写成 ……,不写 ... 或 。。。,也不和“等”连用。
  • 数字一律用半角。

数字(千分位、单位、范围、倍数)、括号、冒号、连接号、英文缩写的细则,见 references/typography.md。文档里出现这些内容时读它。

写一整套产品手册或文档站、需要规划目录和文件名时,读 references/manual-structure.md。

AI 腔清单

自检时逐条对照。左边是要找的写法,右边是改法。

找这种写法改成
开场套话:“随着……的发展”“在当今……”“值得注意的是”“需要指出的是”“让我们来看看”“接下来我们将介绍”删掉,第一句直接说内容
结尾套话:“总的来说”“综上所述”“总而言之”,或重复前文的总结段删掉。确实需要结尾,只写新信息,比如下一步做什么
客套话:“希望对你有帮助”“如有问题欢迎交流”删掉
对比句式:“不是 A,而是 B”“与其说 A,不如说 B”直接说 B
递进句式:“不仅……而且/更……”拆成两个陈述句
硬凑三个:三个排比形容词、每组都是三项的列表有几项写几项
设问自答:“关键是什么?答案很简单:”“原因很简单:”直接给结论
宣传腔形容词:强大、灵活、无缝、全面、极致、优雅、轻松、一站式换成具体事实,没有事实就删
黑话:赋能、抓手、闭环、链路、沉淀、对齐、颗粒度、维度、底层逻辑、范式、打通换成白话。代码或业务里的正式名称(如“调用链路”)保留
破折号 —— 用来插入解释改用逗号、冒号、括号,或拆成两句。全文最多一两处
翻译腔:“进行 + 动词”“通过……的方式”“作为一个……”、一句里多个“的”直接用动词,拆开长定语
过度含糊:“在某种程度上”“在一定情况下可能会”确定就直接说;不确定就说清条件
感叹号、emoji 标题或列表符号句号,纯文字标题
每段都加粗、一两句话也拆成列表、小标题比段落还密按“段落与结构”重排

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 Tech Writing AI skill do?

中文技术文档写作规范。写或修改中文技术文档、开发文档(README、设计文档、接口说明、教程)时使用。

Why use Zh Tech Writing on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing. 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 Tech Writing?

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 Tech Writing?

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

Is the Zh Tech Writing AI skill free?

Yes. It is published on GitHub by leter 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 👇