Z Docx Format Brush

Community

tjxj

z-docx-format-brush

docx 格式刷：从模板 Word 文档提取格式指纹（字体/字号/行距/缩进/对齐/表格边框/封面/分页），然后统一应用到目标 docx，做到与模板格式完全一致。触发词：格式刷、格式统一、统一格式、套用模板格式、参照模板格式、docx格式修复、Word格式不一致、pandoc转出来的docx格式乱、按模板生成docx、公文格式。凡是'参照某个 docx 模板写/改/修复另一个 docx'的任务都用本 skill，包括新建文档按模板排版、修复其他工具（pandoc/其他模型）产出的格式混乱 docx。

Overview

Publisher	tjxj
Repository	`z-skills`
Skill name	`z-docx-format-brush`
Stars	548
Forks	102
Bundled files	5
Links	Skill source Repository

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 tjxj on GitHub. Read the source before you install it.

Installation

Install the Z Docx Format Brush AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/tjxj/z-skills/tree/main/z-docx-format-brush
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.

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/tjxj/z-skills.git /tmp/z-skills
mkdir -p .claude/skills
cp -r /tmp/z-skills/z-docx-format-brush .claude/skills/z-docx-format-brush

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Z Docx Format Brush 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 Z Docx Format Brush 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 Z Docx Format Brush 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.

docx 格式刷（Format Brush）

把一份模板 docx 的格式"刷"到另一份 docx 上。核心思想：格式参数从模板实测出来，收敛到唯一出口应用，凭感觉手调必然不统一。

适用场景

修复场景：已有内容正确但格式混乱的 docx（典型：pandoc / 其他模型转换产出），按模板统一格式
新建场景：从零生成 docx，要求格式与某模板一致
诊断场景：只想知道两份 docx 格式差异在哪

三步工作流

第一步：解剖模板 → 格式指纹

bash
python3 scripts/extract_fingerprint.py "模板.docx"

输出模板的格式指纹（JSON + 可读摘要）：

各样式（Normal/Heading 1-3/Body Text）的字体、eastAsia 中文字体、字号、加粗、颜色
正文段落实测的行距、首行缩进、对齐分布（取众数为准，样式定义常与实际 run 不符）
标题段落实测参数（模板作者往往在 run 层覆盖了样式，必须以 run 实测为准）
封面段落结构（前3段的字号/对齐）
表格：边框有无、单元格字体字号
章节标题是否分页（pageBreakBefore）

为什么要实测而非只看样式表：中文公文类 docx 几乎都在 run 层直接设置仿宋等字体，样式表里可能还是默认值。只信样式表必然刷错。

第二步：诊断目标文件（修复场景）

bash
python3 scripts/extract_fingerprint.py "目标.docx"

对比两份指纹，列出病灶清单。pandoc 产物的典型病灶：

所有 run 字体/字号为 None（裸继承 Body Text/First Paragraph 默认样式 → Calibri/宋体混排）
标题带默认主题蓝（0F4761）
表格无 tblBorders（无边框）
无封面、章节不分页
中文引号开闭反向（"xxx" 被转成 ”xxx“）

第三步：应用格式刷

bash
python3 scripts/apply_format.py "目标.docx" --config fingerprint.json [--out "输出.docx"]

不带 --out 时原地修复。脚本按五层顺序应用（顺序重要，样式层先兜底，run 层再精确覆盖）：

样式层：Normal/Body Text/First Paragraph/Heading 1-3 全部改为模板字体字号，清除颜色 —— 兜住一切继承
段落层：正文统一行距/首行缩进；标题清缩进、按指纹设置字号加粗；第X章 型 Heading 1 居中 + pageBreakBefore
封面层：首段含"文件/报告/方案"等关键词时重做三行式封面（公司名/项目名大字号 + 文档类型更大字号，居中加粗）
表格层：补齐单线 tblBorders、单元格统一字体字号、表头行加粗、行距 1.0、清缩进
文字层：中文引号按开闭配对重排为 “xxx”

关键技术要点（写任何 docx 处理代码前必读）

中文字体要设两遍：run.font.name 只管西文；必须再 rPr.rFonts.set(qn('w:eastAsia'), '仿宋')，否则 Word 中文回落宋体
字号换算：docx 内部是 EMU，磅 = EMU / 12700（如 152400 = 12磅，203200 = 16磅）
首行缩进2字符 ≈ Emu(304800)（12磅正文）或 Emu(406400)（16磅正文），即 2×字号
清颜色：r.font.color.rgb = None 不够，需从 rPr 中 remove w:color 元素
章节分页：往 pPr 里插 w:pageBreakBefore 元素，优于插入分页符 run
新建场景：先准备结构化内容 JSON，再调用 scripts/gen_from_template.py。脚本内的 title()、para() 和 table() 工厂统一应用指纹参数，所有内容只从工厂函数写入。

bash
python3 scripts/gen_from_template.py "content.json" \
  --config fingerprint.json \
  --out "output/doc/输出.docx"

内容 JSON 使用 cover 和 blocks。blocks 支持 heading、paragraph、table、page_break；完整示例见脚本顶部说明。

验证（必做，做完才算完成）

bash
python3 scripts/verify_format.py "输出.docx"

通过标准：

run 字体分布收敛到指纹规定的少数几档（如仿宋12/15/22磅），无 None 无杂色
全部表格有 tblBorders
所有 第X章 Heading 1 有 pageBreakBefore
抽查含引号段落方向正确

验证输出贴给用户看，用表格汇报"病灶 → 修复"对照。

输出约定

修复场景默认原地保存，同时按用户此前要求的目录放置副本
新建场景输出到 output/doc/
汇报时列出格式指纹表（元素/参数）让用户可核对

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 Z Docx Format Brush AI skill do?

Why use Z Docx Format Brush on TypingMind?

Because you install it once and use it with any model. Z Docx Format Brush 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 Z Docx Format Brush in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tjxj/z-skills/tree/main/z-docx-format-brush. 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 Z Docx Format Brush?

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 Z Docx Format Brush?

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

Is the Z Docx Format Brush AI skill free?

It is published on GitHub by tjxj. 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

Feishu Doc

openclaw

OrganizationPopular

Feishu document read/write workflows. Activate when the user mentions Feishu docs, cloud docs, or docx links.

Feishu Drive

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

Feishu Wiki

Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.

Wacli

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

docx 格式刷（Format Brush）

适用场景

三步工作流

第一步：解剖模板 → 格式指纹

第二步：诊断目标文件（修复场景）

第三步：应用格式刷

关键技术要点（写任何 docx 处理代码前必读）

验证（必做，做完才算完成）

输出约定

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now