Word 大师 · Word Master

SkillFiles & storage

Convert Markdown documents to professionally styled DOCX (Word) files with python-docx. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, cover pages, TOC field, watermarks, and page numbers. Supports multiple color themes matching any2pdf (Configurable Academic, Nord, GitHub Light, etc.) and is battle-tested for Chinese technical reports. Use this skill whenever the user wants to turn a .md file into a styled Word document, generate an editable report from markdown, or create a DOCX from markdown content — especially if CJK characters, code blocks, or tables are involved. Also trigger when the user mentions "markdown to docx", "md2docx", "any2docx", "md转word", "md转docx", "生成word", or asks for an "editable document" from markdown source.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Word 大师 · Word Master skill

What this skill tells your AI

The instructions your AI receives, as published by lovstudio/skills in skills/any2docx/SKILL.md and read by ahel’s review.

This skill converts any Markdown file into a professionally styled Word document using Python's python-docx library. It shares the same theme palette as any2pdf and handles all CJK/Latin edge cases correctly.

When to Use

  • User wants to convert .md.docx (Word)
  • User needs an editable document (not PDF)
  • Document contains CJK characters mixed with Latin text
  • Document has fenced code blocks, markdown tables, or lists
  • User wants a cover page, table of contents, or watermark in their DOCX

Quick Start

python lov-any2docx/scripts/md2docx.py \
  --input report.md \
  --output report.docx \
  --title "My Report" \
  --author "Author Name" \
  --theme warm-academic

All parameters except --input are optional — sensible defaults are applied.

Pre-Conversion Options (MANDATORY)

IMPORTANT: You MUST use the AskUserQuestion tool to ask these questions BEFORE running the conversion. Do NOT list options as plain text — use the tool so the user gets a proper interactive prompt. Ask all options in a SINGLE AskUserQuestion call.

Use AskUserQuestion with the following template:

开始转 Word!先帮你确认几个选项 👇

━━━ 📐 设计风格 ━━━
 a) 暖学术    — 陶土色调,温润典雅,适合人文/社科报告
 b) 经典论文  — 棕色调,灵感源自 LaTeX classicthesis,适合学术论文
 c) Tufte     — 极简留白,深红点缀,适合数据叙事/技术写作
 d) 期刊蓝    — 藏蓝严谨,灵感源自 IEEE,适合正式发表风格
 e) 精装书    — 咖啡色调,书卷气,适合长篇专著/技术书
 f) 中国红    — 朱红配暖纸,适合中文正式报告/白皮书
 g) 水墨      — 纯灰黑,素雅克制,适合文学/设计类内容
 h) GitHub    — 蓝白极简,程序员熟悉的风格
 i) Nord 冰霜 — 蓝灰北欧风,清爽现代
 j) 海洋      — 青绿色调,清新自然
 k) 投资报告  — 楷体+深红,专业严谨,适合投资/尽调报告

━━━ 💧 水印 ━━━
 1) 不加
 2) 自定义文字(如 "DRAFT"、"内部资料")

示例回复:"a, 水印:仅供内部参考"
直接说人话就行,不用记编号 😄

Mapping User Choices to CLI Args

ChoiceCLI arg
Design style a-k--theme with value from table below
Watermark text--watermark "文字"

Theme Name Mapping

Choice--theme value
a) 暖学术warm-academic
b) 经典论文classic-thesis
c) Tuftetufte
d) 期刊蓝ieee-journal
e) 精装书elegant-book
f) 中国红chinese-red
g) 水墨ink-wash
h) GitHubgithub-light
i) Nordnord-frost
j) 海洋ocean-breeze
k) 投资报告invest-report

Architecture

Markdown → Strip frontmatter → Preprocess (split merged headings) → Parse (code-fence-aware) → python-docx Document → .docx

Key components:

  1. CJK font switching: _split_mixed() detects CJK runs and assigns Songti SC / SimSun / Noto CJK
  2. Inline markdown: _parse_inline() handles bold, italic, code, links
  3. Images: Local paths (relative to .md) and remote URLs — auto-downloaded and embedded via add_picture()
  4. Code blocks: Shaded paragraph with monospace font and border
  5. Tables: Header row with accent background, alternating row shading
  6. Watermark: VML-based diagonal watermark in header (Word-native)
  7. TOC: Field code with static fallback entries; updateFields=true triggers auto-refresh on open
  8. YAML frontmatter: Automatically stripped (won't leak status: draft etc. into output)
  9. Adaptive cover title: Font size scales down for long titles (36pt → 22pt)

Configuration Reference

ArgumentDefaultDescription
--input(required)Path to markdown file
--outputoutput.docxOutput DOCX path
--titleFrom first H1Document title for cover page
--subtitle""Subtitle text
--author""Author name
--dateTodayDate string
--version""Version string for cover
--watermark""Watermark text (empty = none)
--themewarm-academicColor theme name
--covertrueGenerate cover page
--toctrueGenerate table of contents
--header-title""Report title in page header
--footer-leftauthorBrand/author in footer
--stats-line""Stats on cover
--stats-line2""Second stats line
--edition-line""Edition line on cover
--code-max-lines30Max lines per code block

Dependencies

pip install python-docx --break-system-packages

Runtime context (shared)

运行前读取本 Skill 包的 skill.yaml,由宿主提供 skill-runtime/v1 上下文。字段解析顺序为:当前请求、项目上下文、个人 Preferences、品牌 Profile、通用默认值。

  • 只使用 Manifest 声明的字段;Profile 保存公开品牌事实,Preferences 保存个人工作偏好。
  • required: true 字段缺失时,按 Manifest 的问题配置向用户提出一个聚焦问题;用户明确同意后再保存回答。
  • 报错提供可复制的 context_id、字段路径与来源,诊断内容避开秘密、完整私人路径和原始配置。

通用反馈闭环

用户在 Skill 驱动任务中提出修改意见时,继续当前产物前必须执行:

  1. 先判断意见是 task-specific(仅本次)还是 reusable(可跨任务复用)。
  2. task-specific 只修改当前任务,不改 Skill。
  3. reusable 先确定作用域:领域规则先更新对应 canonical Skill;适用于所有 Skill 的规则先更新共享规范。
  4. 完成规则更新、版本、lint 与分发核验后,再把修改应用到当前任务。
  5. reusable 修改会使此前的“确认”“继续”“发吧”失效;完成当前产物修改和回读后必须停下,等待用户下一步指示,不自动进入发布、提交或其他外部写入。

Signals

GitHub stars
66
Forks
17
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
lov-any2docx
Source
github.com/lovstudio/skills