markitdown

Convert PDFs, DOCX, PPTX, and other formats into Markdown.

4|Updated Jan 6, 2026
One-click install
npx skills add https://github.com/flight505/claude-project-planner --skill markitdown-flight505
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/flight505/claude-project-planner/tree/main/project_planner/.claude/skills/markitdown
Command: npx skills add https://github.com/flight505/claude-project-planner --skill markitdown-flight505

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

MarkItDown streamlines the tedious task of turning diverse documents into clean, token-efficient Markdown suitable for LLM ingestion and knowledge work.

Core Features & Use Cases

  • Format support: PDFs, DOCX, PPTX, XLSX, EPUB, images with OCR, audio transcripts, HTML, CSV, JSON, XML, ZIP archives, and YouTube transcripts.
  • AI-enhanced descriptions: Optional OpenRouter/OpenAI integrations to generate detailed image and slide descriptions.
  • Batch processing: Parallel conversions across directories with optional plugin support.
  • Use Case: Convert a research paper with figures into a structured Markdown draft with front matter and citations for literature reviews.

Quick Start

To convert a PDF, run: markitdown document.pdf Or use the Python API:

  1. md = MarkItDown()
  2. result = md.convert("document.pdf")
  3. print(result.text_content)

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDFs and Word documents to Markdown for LLM ingestion?

You can convert PDFs and Word documents to Markdown by running the markitdown command-line tool or using its Python API to transform files into clean, token-efficient text. It processes DOCX, PPTX, XLSX, HTML, and various other formats for immediate LLM ingestion.

Can I batch convert multiple documents to Markdown simultaneously?

Yes, batch processing supports parallel conversions across entire directories. You can process multiple files simultaneously with optional plugin support to generate structured Markdown outputs from diverse document collections.

Do I need an OpenAI or OpenRouter API key to convert documents to Markdown?

No, an OpenAI or OpenRouter API key is not required for standard document conversion. These integrations are optional and only needed if you want AI-enhanced descriptions for images and slide narratives during the conversion process.

What file formats are supported when converting documents to Markdown?

Supported formats include PDFs, DOCX, PPTX, XLSX, EPUB, HTML, CSV, JSON, XML, and ZIP archives. It also handles images with OCR, audio transcripts, and YouTube transcripts to produce structured Markdown.

Does this document conversion tool work with Python for knowledge base ingestion?

Yes, it runs on Python 3.10+ and provides a dedicated Python API for converting documents. The output is clean, structured Markdown designed specifically for efficient ingestion by LLMs and knowledge bases.

What is the best way to extract text and figures from a research paper into Markdown?

The best way is using this tool to convert research papers with figures into a structured Markdown draft. It extracts text and utilizes optional AI integrations to generate detailed descriptions of images and slide narratives.