pdf-to-markdown

Convert PDF documents to Markdown with automatic mode selection.

Updated Aug 27, 2026

Search Tags:#pdf #markdown #conversion #document-processing #code-blocks #text-extraction

Ready to run

npx skills add https://github.com/talent-factory/claude-plugins --skill pdf-to-markdown-talent-factory

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf-to-markdown
Source: https://github.com/talent-factory/claude-plugins/tree/main/plugins/core/skills/pdf-to-markdown
Command: npx skills add https://github.com/talent-factory/claude-plugins --skill pdf-to-markdown-talent-factory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyMuPDF, Pillow, pdf2image, anthropic, tqdm, pymupdf4llm, and includes scripts (resource) components.

What problem does it solve?

Converts PDF documents to Markdown with automatic mode selection.

Core Features & Use Cases

Fast text extraction using PyMuPDF for simple PDFs
Vision-based analysis for complex layouts including code blocks and tables
Output Markdown file with optional extracted images or page-specific content

Quick Start

Convert a PDF to Markdown by selecting the file and choosing the desired mode (fast for simple text or vision for complex layouts).

Frequently Asked Questions about pdf-to-markdown

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

FAQPage Schema

How do I convert a PDF to Markdown without losing code blocks and tables?▼

You can convert a PDF to Markdown by using vision-based analysis to process complex layouts, ensuring code blocks and tables are accurately extracted and properly formatted in the output Markdown file.

What's the best way to extract text from large administrative PDFs quickly?▼

For fast text extraction from simple PDFs, you can use PyMuPDF processing mode to quickly convert administrative documents into structured Markdown files without engaging slower vision-based analysis.

Does PyMuPDF support converting specific page ranges to Markdown?▼

Yes, the conversion process supports page-range processing, allowing you to target specific sections of a PDF document and output only the selected pages as a Markdown file with optional extracted images.

Can I extract images alongside text when converting PDFs to Markdown?▼

Yes, the tool outputs a structured Markdown file plus optional extracted images, allowing you to capture visual content from the PDF document while preserving the text structure during conversion.

When should I use vision-based analysis instead of fast extraction for PDF conversion?▼

Vision-based analysis is necessary when your PDF contains complex layouts with code blocks or tables, while fast PyMuPDF extraction is sufficient for simple text documents without intricate formatting.

Why does PDF to Markdown conversion fail on complex technical documents?▼

Complex technical PDFs often fail with simple extraction because of code blocks and tables; switching to vision-based analysis via page images handles these intricate layouts to produce accurate Markdown.