A lightning-fast CLI tool to transform Word documents, PowerPoint presentations, and Excel spreadsheets into clean Markdown format.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install doc2md
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 doc2md 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 Doc2MD - Quick Office Parser?
Doc2MD is a robust document-to-markdown converter powered by the MinerU Open API, designed specifically for developers and AI agents who need to ingest structured content from legacy office formats. It bridges the gap between binary document formats and LLM-friendly text by preserving essential document structures such as tables, headers, and lists.
As a featured part of the Openclaw Skills ecosystem, this tool eliminates the friction of manual data entry or complex parsing logic. It allows users to process DOCX, PPTX, and XLSX files—whether stored locally or hosted at a URL—into formatted Markdown in seconds, all without requiring any authentication or API keys for standard use cases.
Doc2MD - Quick Office Parser Use Cases
- Extracting text and tables from corporate reports (.docx) for AI summarization.
- Converting presentation slides (.pptx) into structured notes for knowledge management.
- Turning complex Excel data into Markdown tables for documentation or web publishing.
- Integrating automated document ingestion into AI agent workflows to read shared office files.
How Doc2MD - Quick Office Parser Works
- The user provides a local file path or a remote URL pointing to a supported office document (DOCX, PPTX, XLS, XLSX).
- The skill invokes the
mineru-open-api flash-extractcommand to transmit the file to the MinerU cloud engine. - The engine parses the document structure, identifying text blocks, hierarchy, and tabular data.
- The parsed content is converted into a clean Markdown stream.
- The Markdown output is either returned to the terminal/AI agent or saved to a specified output directory for further processing.
Doc2MD - Quick Office Parser Setup
You can install the necessary components for this skill using several package managers. Choose the one that fits your environment:
# Install via npm
npm install -g mineru-open-api
# Install via uv
uv tool install mineru-open-api
# Install via Go (Linux/macOS)
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
Once installed, you can verify the setup by running mineru-open-api flash-extract --help.
Doc2MD - Quick Office Parser Data Schema & Taxonomy
The skill focuses on a non-destructive extraction process that maps office components to Markdown elements. The following table describes the mapping taxonomy:
| Source Element | Markdown Output |
|---|---|
| Headers (H1-H6) | Markdown Headers (# to ######) |
| Paragraphs | Standard Text Blocks |
| Tables | GitHub Flavored Markdown (GFM) Tables |
| Lists | Unordered (-) or Ordered (1.) Lists |
| Images | Placeholders (Note: Embedded images are not extracted as files in flash-mode) |
Constraints:
- Max File Size: 10MB (Flash Mode)
- Max Page Count: 20 Pages (Flash Mode)
Doc2MD - Quick Office Parser Advanced Features
- URL Support: Directly parse documents from the web without downloading them first.
- Precision Extraction: For files up to 200MB or 600 pages, the skill supports a more robust
extractcommand (requires authentication). - Custom Output Routing: Use the
-oflag to direct converted Markdown files to specific project directories. - Zero-Auth Workflow: Operates fully without API keys, making it ideal for portable Openclaw Skills implementations.
SKILL.md
Loading
Related Openclaw Skills
Token Monitor
A powerful monitoring tool for OpenClaw that analyzes session logs to track token consumption and skill success rates.
Feishu Literature Manager
A powerful automation tool that synchronizes PubMed research data directly into Feishu Bitable with full metadata and Chinese translations.
Word / DOCX
A specialized skill for managing Microsoft Word documents with full support for OOXML structures, styles, and tracked changes.
Automation Tester Roadmap
A professional career development platform that generates data-driven learning pathways for automation testing professionals.
Love Advisor
Love Advisor provides grounded, practical relationship guidance for navigating complex dating scenarios and emotional challenges.
Blood Glucose Management Assistant
A comprehensive blood glucose management skill designed to record, analyze, and predict blood sugar trends while providing personalized dietary and exercise advice.
METADATA
Featured*
