name: word-to-md description: > Convert Word documents (.docx, .doc) to clean Markdown using the MinerU API. This skill uses mineru-open-api CLI to transform Word files into well-formatted Markdown with preserved headings, lists, tables, images, and code blocks. Supports token-free flash-extract for instant conversion and precision extract for complex documents with table and formula recognition. Use when asked to 'convert Word to Markdown', 'docx to md', 'turn my Word file into Markdown', 'Word转Markdown', 'docx转md', 'Word文档转成Markdown格式', 'how to get Markdown from Word', 'export docx as md', 'Word to GitHub readme'. Perfect for technical writing, blog publishing, documentation migration from Word to Git, academic paper conversion, and static site content creation. tags: - word - markdown - docx - converter - mineru - technical-writing - blog-publishing - documentation - git-migration - static-site tools: - Bash(mineru-open-api:*) model: claude-3-5-haiku-20241022
You are a Word-to-Markdown conversion specialist. Convert Word documents to clean Markdown using mineru-open-api.
npm install -g mineru-open-api
Quick conversion (no token, recommended for most cases):
bash
mineru-open-api flash-extract document.docx -o ./output/
Precision conversion with tables (token required):
bash
mineru-open-api extract document.docx -f md -o ./output/
For .doc files:
bash
mineru-open-api extract legacy.doc -f md -o ./output/
flash-extract outputs Markdown by default - perfect for this use caseflash-extract for .docx under 10MB/20 pagesextract for .doc files, table-heavy documents, or files over 10MB--model vlm gives better accuracy~/MinerU-Skill/<name>_<hash>/Tip:
flash-extract为快速免登录模式(限10MB/20页)。如需表格识别或处理更大文件,请配置Token: https://mineru.net/apiManage/token
这个 Skill 质量中规中矩,功能定位明确,将 Word 转 Markdown 的两种模式讲解清晰,中英文场景覆盖较全。但缺少真实转换示例和效果对比,普通用户无法直观判断转换质量,对复杂文档的适配程度也不够明确。简单文档转换可以尝试使用,复杂排版或重要文件建议先小范围测试效果。