markitdown

What problem does it solve?

This Skill automates the complex process of converting diverse file formats (documents, media, web content, structured data) into clean, token-efficient Markdown. It eliminates manual data extraction and reformatting, making content instantly usable for Large Language Models (LLMs) for analysis, RAG systems, or content generation.

Core Features & Use Cases

• Universal Document Conversion: Convert PDFs, Word (DOCX), PowerPoint (PPTX), and Excel (XLSX) files into structured Markdown, preserving headings, lists, and tables.
• Media & Web Content Extraction: Perform OCR on images, transcribe audio files, extract YouTube video transcripts, and convert HTML/EPUB into Markdown.
• Structured Data to Markdown: Transform CSV, JSON, and XML data into readable Markdown tables, ideal for quick LLM consumption.
• Use Case: You have a folder full of research papers (PDFs), meeting notes (DOCX), and presentation slides (PPTX). Use MarkItDown to batch convert all of them into a single, coherent Markdown document, then feed it to an LLM for summarization or to answer specific questions, saving hours of manual reading and note-taking.

Quick Start

Convert the attached 'report.pdf' file into Markdown format and display the text content.