markitdown

Convert PDFs, Word documents, PowerPoint slides, and Excel sheets to Markdown.

3|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill markitdown-ramanebrahimi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/RamanEbrahimi/raman-marketplace/tree/main/plugins/agentic-research/skills/scientific-skills/markitdown
Command: npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill markitdown-ramanebrahimi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, openpyxl, python-docx, ezPDF3, pyxlsb, reportlab, Pillow, opencv-python, pytesseract, markitdown[all], and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill converts various file formats to Markdown, making it easier to share and process documents in a text-friendly format.

Core Features & Use Cases

  • File Conversion: Convert PDFs, Word documents, PowerPoint slides, Excel sheets, and more to Markdown.
  • AI-Enhanced Image Descriptions: Generate detailed descriptions of images for accessibility and context.
  • Visual Enhancements: Generate scientific schematics for better visualization in documents.
  • Use Case: When you have a complex document with images and diagrams, this Skill can convert it to Markdown and provide AI-generated descriptions for the images.

Quick Start

To convert a PDF to Markdown, use the command: python scripts/generate_schematic.py "your diagram description" -o figures/output.png

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDF and Word documents to Markdown format?

You can convert PDFs, Word documents, PowerPoint slides, and Excel sheets to Markdown using this Skill. It leverages libraries like pypdf, pdfplumber, and python-docx for text extraction, streamlining document processing workflows.

Can I generate descriptions for images when converting files to Markdown?

Yes, this Skill generates AI-enhanced image descriptions when converting files to Markdown. It uses OCR capabilities via pytesseract and image processing libraries to provide context for images within the document.

Does this file conversion tool support Excel sheets and PowerPoint slides?

Yes, the tool supports Excel sheets and PowerPoint slides by utilizing openpyxl and pyxlsb dependencies. It extracts content from these formats and converts them into a text-friendly Markdown structure.

What is the best way to create scientific diagrams from text descriptions?

The best way to create scientific diagrams is by running the built-in schematic generation script. You provide a text description, and the script outputs a visual schematic image to enhance your Markdown document.

What Python libraries are required for PDF text extraction and OCR processing?

Required Python libraries include pypdf, pdfplumber, and pdf2image for PDF text extraction, alongside pytesseract and opencv-python for OCR processing. These dependencies enable comprehensive document conversion to Markdown.

Why use Markdown for scientific research document workflows?

Markdown is used for scientific research workflows because it provides a highly text-friendly format that simplifies sharing and processing complex documents. It easily integrates extracted text, AI image descriptions, and generated scientific schematics.