Word to Markdown (MinerU) for Openclaw

Effortlessly convert Word documents into clean, structured Markdown files using the MinerU API.

veeicwgy
v0.2.0
Apr 6, 2026
0
852
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install word-to-md

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install word-to-md using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Word to Markdown (MinerU)?

The word-to-md skill is a powerful utility designed for Openclaw Skills that bridges the gap between legacy document formats and modern Markdown-based workflows. It utilizes the mineru-open-api CLI to perform high-fidelity conversions of .doc and .docx files, ensuring that complex elements like nested lists, tables, and embedded images remain intact. Whether you are publishing a blog post or migrating technical specifications, this tool streamlines the transition to text-based documentation.

By integrating this skill, AI agents can automate the tedious process of manual reformatting. It offers two primary modes: a fast, token-free flash extraction for smaller documents and a high-precision extraction for complex layouts requiring advanced recognition logic. This flexibility makes it a cornerstone for teams moving towards docs-as-code practices and helps developers maintain a single source of truth in their repositories.

Word to Markdown (MinerU) Use Cases

  • Migrating legacy Word documentation to Git-based repositories for better version control.
  • Converting technical manuscripts into Markdown for deployment on static site generators like Jekyll or Hugo.
  • Rapidly extracting structured content from .docx files for blog publishing.
  • Automated conversion of academic papers including tables and formulas into readable web formats.

How Word to Markdown (MinerU) Works

  1. The AI agent identifies a Word document (.doc or .docx) requiring conversion based on user request.
  2. The skill selects the optimal extraction method from the mineru-open-api suite based on file size and complexity.
  3. Documents under 10MB or 20 pages trigger the flash-extract command for instant, token-free processing.
  4. Legacy .doc files or documents with complex table structures are processed using the precision extract mode.
  5. The tool generates structured Markdown content and saves it along with extracted assets into a dedicated output directory.

Word to Markdown (MinerU) Setup

To begin using this skill, you must install the MinerU Open API CLI globally on your system:

npm install -g mineru-open-api

While flash-extract works without authentication, high-precision tasks or documents with heavy table usage require an API token. You can obtain your token from the MinerU dashboard and configure it in your environment variables for seamless operation.

Word to Markdown (MinerU) Data Schema & Taxonomy

The skill manages data through a structured output system to ensure file integrity and organization:

Property Detail
Supported Input .doc, .docx formats
Primary Output Clean Markdown (.md) file
Output Directory ~/MinerU-Skill/<document_name>_<hash>/
Asset Handling Images and media are extracted into local sub-directories
Schema Metadata Preserves headings, tables, lists, and code block formatting

Word to Markdown (MinerU) Advanced Features

  • Supports flash-extract for fast, token-free processing of standard documents.
  • High-fidelity table and formula recognition for academic and technical papers.
  • Multi-format support covering both legacy .doc and modern Word .docx files.
  • Optional integration with the VLM model for superior document layout analysis and accuracy.
  • Automatic generation of unique output directories to prevent file overwrites during batch processing tasks.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*