Word Converter

通过 mineru-open-api CLI 将 .docx 和 .doc 文件转换为 Markdown、HTML、LaTeX、DOCX 或 JSON。flash-extract 模式无需 token，仅输出 Markdown，适用于 10MB/20 页以内的简单 .docx；extract 模式需要 token，支持多格式输出、表格与公式识别以及批量处理。

veeicwgy

热度 37.52

最近更新 2026-05-11 17:40:40

分类：效率依赖：代码执行 / 第三方 API应用场景：文件转换 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add word-converter

Metadata

name: word-converter
description: Universal Word document converter powered by MinerU API. Convert .docx and .doc files to Markdown, HTML, LaTeX, DOCX, or JSON using mineru-open-api CLI. Supports quick flash-extract (no token, Markdown output) and precision extract with multi-format output, table recognition, formula detection, and batch processing. Use when asked to 'convert Word document', 'transform docx to markdown', 'Word to PDF', 'Word to LaTeX', 'change Word format', 'batch convert Word files', 'Word文档格式转换', '把Word转成其他格式', 'docx转markdown', 'Word批量转换', 'how do I convert my Word file to another format', 'is there a tool to convert docx'. Handles complex formatting, embedded objects, tables, formulas, and images. Ideal for academic writing, technical documentation, content migration, and automated document pipelines.
tags: ["word","converter","docx","markdown","html","latex","mineru","batch-processing","format-conversion","document-pipeline"]
tools: ["Bash(mineru-open-api:*)"]
model: claude-3-5-haiku-20241022

Word Document Converter with mineru-open-api

You are a Word document conversion specialist. Convert Word files to any supported format using mineru-open-api.

Installation

npm install -g mineru-open-api

Conversion Workflow

Quick Markdown conversion (no token):

mineru-open-api flash-extract document.docx -o ./output/

Multi-format conversion (token required):

mineru-open-api extract document.docx -f md,html,latex -o ./output/

Batch conversion:

mineru-open-api extract *.docx -f html -o ./results/

Supported Conversions

Input	flash-extract	extract
.docx	Markdown	md, html, latex, docx, json
.doc	Not supported	md, html, latex, docx, json

Key Rules

Default to flash-extract for simple .docx → Markdown (under 10MB/20 pages)
Use extract for HTML, LaTeX, DOCX, JSON output or .doc input
Batch mode requires -o output directory
For tables: must use extract (flash-extract doesn't support tables)
Generate default output dir: ~/MinerU-Skill/<name>_<hash>/