skills.rest
silverstein
silversteinCOMMUNITY
Explore all skills by this author →
Website𝕏@matsilversteinGitHub

markitdown

Convert PDFs, Office documents, web content, and media into Markdown.

21|2|Updated Dec 8, 2025
Search Tags:#ocr#markdown#document conversion#rag#audio transcription#azure document intelligence
One-click install
npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill markitdown-silverstein
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/markitdown
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill markitdown-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It helps you quickly extract readable text and structure from many file types (documents, spreadsheets, web pages, images, and audio) and convert them into clean Markdown that’s easier for LLMs to process.

Core Features & Use Cases

  • Multi-format conversion: Convert PDFs, Office docs (DOCX/XLSX/PPTX), HTML/web pages, EPUBs, CSV/JSON/XML, and archives like ZIP into Markdown.
  • Image and media extraction: OCR text from images, capture EXIF metadata, and transcribe audio to text.
  • Optional quality upgrades: Use Azure Document Intelligence for complex PDFs and enable LLM-powered image descriptions for diagrams, figures, and slide visuals.
  • Use case examples: Convert a research PDF into Markdown for RAG, transcribe a meeting audio file into searchable notes, or convert a mixed-format dataset export (CSV/JSON) into consistent Markdown tables.

Quick Start

Ask the system to convert your input file to Markdown using MarkItDown, for example: convert attached_file.pdf into clean Markdown and return the extracted 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 Office documents to Markdown for RAG ingestion?▼

You convert PDFs and Office documents to Markdown by passing files to the system, which preserves document structure and produces clean token-efficient text optimized for downstream LLM analysis.

What is the best way to transcribe audio and extract YouTube transcripts into text?▼

Audio transcription and YouTube transcript extraction are handled by converting media files into text, capturing speech and dialogue as structured Markdown content for downstream analysis.

Does this tool support OCR for extracting text from images and document scans?▼

Yes, OCR for images is supported for extracting readable text and capturing EXIF metadata, with optional LLM-powered descriptions for diagrams and slide visuals.

Can I convert structured data formats like CSV, JSON, and XML into Markdown tables?▼

Yes, structured data formats like CSV, JSON, and XML can be converted into consistent Markdown tables, preserving document structure for downstream analysis.

Do I need Azure Document Intelligence to process complex PDF layouts?▼

You do not need Azure Document Intelligence by default, but it is optionally supported to enhance layout extraction and image descriptions when processing complex PDFs.

How do I batch convert a directory of mixed file types into LLM-optimized Markdown?▼

Batch directory conversion is supported, allowing you to process mixed file types like documents, spreadsheets, and archives into LLM-optimized Markdown in one pass.

Related Skills

Explore More Education & Research Skills→
Xueheng-LiXueheng-Li
4

markitdown

Convert diverse file formats into LLM-optimized Markdown.

Community
Advanced
mupengi-botmupengi-bot
11

rag-engineer

Design RAG systems with embedding models, vector databases, and retrieval optimization.

Community
Advanced
librefanglibrefang
10

vector-db

Design and optimize vector search systems for embedding-based retrieval.

Official
Advanced
hochoa13hochoa13

ocr-and-documents

Extracts text and tables from PDFs, images, and other document formats via OCR and parsing tools.

Community
Advanced