A high-performance document conversion utility that leverages the MinerU engine to transform Microsoft Word files into well-structured, readable Markdown.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install doc-to-markdown
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install doc-to-markdown 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 Doc To Markdown?
Doc To Markdown is a specialized document intelligence utility designed to bridge the gap between legacy Word formats and modern, Markdown-based workflows. By utilizing the advanced MinerU engine from OpenDataLab, this tool ensures that headings, tables, lists, and paragraph structures are preserved during the conversion process. It is an essential addition to the Openclaw Skills ecosystem for developers and technical writers who need to migrate content from .doc or .docx files into GitHub, Notion, or Obsidian.
The tool offers two primary modes: a rapid flash-extract mode for standard .docx files that functions without an API token, and a full extraction mode for complex layouts and legacy .doc files. Whether you are handling a single local file or a remote URL, this skill provides a seamless way to integrate document parsing into your automated AI agent workflows.
Doc To Markdown Use Cases
- Migrating legacy technical documentation from Microsoft Word to a static site generator or wiki.
- Converting .docx reports into clean Markdown for version control in GitHub repositories.
- Extracting formatted text from Word documents to be used as context for AI agents using Openclaw Skills.
- Batch processing document archives to modernize content for knowledge bases like Obsidian or Notion.
- Rapidly previewing the content of a Word file within a terminal or CLI environment.
How Doc To Markdown Works
- The user provides a path to a local .doc/.docx file or a public URL.
- For .docx files, the tool can utilize the flash-extract method for instant conversion without authentication.
- For legacy .doc files or complex layouts, the tool authenticates via the MINERU_TOKEN to access full document intelligence features.
- The MinerU engine parses the document structure, identifying semantic elements like headers, lists, and tables.
- The tool generates a clean Markdown output, which is either streamed to stdout for piping or saved to a specified directory.
Doc To Markdown Setup
To integrate this utility into your workflow, install the mineru-open-api package via npm or Go. This ensures your environment is ready to leverage Openclaw Skills for document processing.
# Install via npm
npm install -g mineru-open-api
# Or install via Go (macOS/Linux)
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
# For .doc support, set up your authentication token
export MINERU_TOKEN="your-token-here"
Doc To Markdown Data Schema & Taxonomy
The skill manages document conversion through specific command flags and output redirections. Below is the organizational structure for processed data:
| Feature | Specification |
|---|---|
| Input Formats | .doc, .docx (Local or URL) |
| Output Format | Standard Markdown (.md) |
| Primary Output | stdout (default) or File Directory (-o flag) |
| Metadata Support | Language hints (--language), Page ranges (--pages) |
| Error Handling | Progress and status messages are routed to stderr to keep stdout clean |
Doc To Markdown Advanced Features
- Flash-extract capability for .docx allowing for token-free conversions up to 10MB or 20 pages.
- Multilingual support with language hints to improve OCR and parsing accuracy for English and Chinese.
- Remote file processing by passing a URL directly to the CLI tool.
- Granular control over document segments by specifying exact page ranges for extraction.
- Stream-ready architecture allowing the output to be piped directly into other Openclaw Skills or CLI utilities.
SKILL.md
Loading
Related Openclaw Skills
HTML Analysis
A document intelligence skill powered by MinerU for transforming complex HTML files into structured, hierarchical Markdown content.
DOCX Toolkit
A comprehensive suite of tools for extracting structured text, complex tables, and high-quality images from modern and legacy Microsoft Word documents.
Mx Toolbox
An integration for Mendix developers to automate project management and code quality tasks through the Membrane framework.
FX SDK Agent Skill
A specialized skill for building AI agent integrations with the FX Protocol TypeScript SDK to manage leverage positions, cross-chain bridging, and yield-bearing fxSAVE assets.
Skill Starter
A professional scaffolding engine for rapidly generating standardized, reviewable AI agent skill projects.
PDF to LaTeX
A specialized tool that leverages the MinerU engine to transform complex PDF documents, including academic papers and technical reports, into editable LaTeX source code.
METADATA
Featured*
