skills.rest
xdanger
xdangerCOMMUNITY
Explore all skills by this author →
Website𝕏@xdangerGitHub

marker

Convert PDFs, EPUBs, PPTX, DOCX, XLSX, HTML, and images into Markdown, JSON, or HTML.

Updated Dec 20, 2025
Search Tags:#pdf#markdown#llm#json#data-extraction#document-conversion#marker
One-click install
npx skills add https://github.com/xdanger/claude-plugins --skill marker
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: marker
Source: https://github.com/xdanger/claude-plugins/tree/main/plugins/marker/skills/marker
Command: npx skills add https://github.com/xdanger/claude-plugins --skill marker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts documents (PDFs, EPUBs, PPTX, DOCX, XLSX, HTML, and images) into clean Markdown/JSON/HTML with structured extraction of tables, math, and forms, leveraging marker-pdf with Claude Haiku LLM enhancements.

Core Features & Use Cases

  • Convert a wide range of document formats into Markdown/JSON/HTML while preserving structure and layout.
  • Extract tables, equations, forms, and inline content with improved accuracy using LLM augmentation.
  • Use in workflows for document digitization, content reuse, archival processing, and knowledge extraction from documents.

Quick Start

Run marker_single on a document to convert it to Markdown/HTML/JSON output with optional image preservation.

Frequently Asked Questions about marker

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

FAQPage Schema
How do I convert PDF to Markdown while preserving tables and math equations?▼

You can convert PDF documents to Markdown by using Marker with LLM augmentation. It extracts tables, equations, and forms with improved accuracy, outputting clean Markdown, JSON, or HTML formats.

What is the best way to extract structured data from DOCX and EPUB files?▼

The best way to extract structured data from DOCX and EPUB files is using Marker. It converts these formats into Markdown or JSON while preserving the document's original layout and inline content.

Does document conversion to Markdown require a specific LLM backend?▼

Document conversion requires a configurable LLM backend, defaulting to Claude Haiku but supporting OpenAI or Ollama alternatives. This LLM integration drives the enhanced extraction and formatting of complex document elements.

Can I extract tables and forms from PPTX and XLSX files for content reuse?▼

Yes, you can extract tables and forms from PPTX and XLSX files for content reuse. Marker supports these formats alongside PDFs, EPUBs, DOCX, HTML, and images, enabling comprehensive document digitization workflows.

Do I need Python and PyTorch to run marker for PDF data extraction?▼

Yes, you need Python 3.10+ and PyTorch installed to run marker for PDF data extraction. These are required dependencies for executing the marker-pdf[full] package and processing documents into structured outputs.

Why use an LLM-enhanced tool for converting documents to JSON instead of standard parsers?▼

Standard parsers often fail on complex layouts, whereas an LLM-enhanced tool provides superior accuracy for tables, math, and forms. This approach ensures cleaner Markdown and JSON output for archival processing and knowledge extraction.

Related Skills

Explore More Content & Communication Skills→
mfmezgermfmezger
5

convert-to-markdown

Convert PDF, DOCX, PPTX, XLSX, HTML, EPUB, and images to Markdown.

Community
Intermediate
zzafergokzzafergok
1

markdown-to-html-skill

Convert Markdown documents to HTML using marked.js, pandoc, gomarkdown, or static site generators.

Community
Intermediate
Victory-HugoVictory-Hugo
1

markitdown

Convert PDF, DOCX, PPTX, XLSX, and other documents to Markdown.

Community
Advanced
manuelbrandner85manuelbrandner85

pdf

Extracts text, tables, and images from PDFs with OCR support.

Community
Advanced