markitdown-converter

Convert documents to Markdown for downstream AI processing.

2|Updated Apr 27, 2026
One-click install
npx skills add https://github.com/zunyiqingfeng-code/skills --skill markitdown-converter-zunyiqingfeng-code
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown-converter
Source: https://github.com/zunyiqingfeng-code/skills/tree/main/markitdown-converter
Command: npx skills add https://github.com/zunyiqingfeng-code/skills --skill markitdown-converter-zunyiqingfeng-code

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, and includes scripts (resource) components.

What problem does it solve?

Converting documents of various formats into Markdown while preserving structure and readability, reducing manual reformatting and enabling seamless content processing by LLMs.

Core Features & Use Cases

  • Multi-format support: PDFs, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images, HTML, and plain text.
  • OCR and AI-assisted description: OCR for images and scanned PDFs, plus optional LLM-based image descriptions for rich Markdown.
  • Batch processing and plugin extensibility: process folders and leverage plugins to extend capabilities for specialized formats.
  • Use cases: publish knowledge bases, migrate content between systems, or archive documents in a clean Markdown format.

Quick Start

Convert a document by providing its path and MarkItDown will output a Markdown file with preserved structure.

Frequently Asked Questions about markitdown-converter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDF documents to Markdown while preserving structure?

This tool converts PDF documents to Markdown by applying multi-format parsing and OCR to preserve structure and readability, outputting a clean Markdown file for downstream AI processing.

Can I batch convert Word and Excel files into Markdown format?

Yes, you can batch convert Word and Excel files into Markdown. The tool processes entire folders of documents, applying multi-format parsing to generate standardized Markdown outputs.

Does converting scanned PDFs to Markdown require OCR?

Yes, converting scanned PDFs to Markdown requires OCR. The tool leverages OCR and optional Azure Document Intelligence to extract text from images and scanned documents for rich Markdown output.

What is the best way to extract text from images for a knowledge base?

The best way to extract text from images for a knowledge base is using OCR and optional LLM-based image descriptions, converting visual content into rich Markdown for seamless content processing.

Do I need a specific MarkItDown setup to convert PowerPoint presentations?

Yes, you need a compatible MarkItDown setup with multi-format parsing to convert PowerPoint presentations to Markdown. Plugin extensibility is also available for specialized formats.

Why does my document conversion lose formatting when migrating content?

Document conversion may lose formatting if the setup lacks proper multi-format parsing or plugins. This tool reduces manual reformatting by preserving document structure and readability during Markdown conversion.