do.marker

Convert PDF documents to Markdown while preserving LaTeX formulas and structure.

6|3|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/dull-bird/DeepOrbit --skill do-marker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: do.marker
Source: https://github.com/dull-bird/DeepOrbit/tree/main/skills/do.marker-pdf
Command: npx skills add https://github.com/dull-bird/DeepOrbit --skill do-marker

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Convert PDF documents into clean, editable Markdown while preserving LaTeX formulas, equations, and the original document structure so that academic and technical content becomes searchable and easy to edit in an Obsidian vault.

Core Features & Use Cases

  • Preserves LaTeX math and equations during extraction to retain mathematical fidelity for academic papers and technical reports.
  • Provides a Python API and CLI wrapper around the marker_single tool with configurable timeout and an option to keep or clean temporary output.
  • Use Case: Convert an arXiv PDF into a Markdown note with intact formulas and section structure for inclusion in an Obsidian research vault.

Quick Start

Convert the attached paper.pdf to Markdown preserving LaTeX formulas and return the Markdown content.

Frequently Asked Questions about do.marker

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

FAQPage Schema
How do I convert a PDF to Markdown while preserving LaTeX formulas and document structure?

To convert a PDF to Markdown while preserving LaTeX formulas, use a tool that wraps the marker_single CLI to extract academic papers into clean, editable Markdown with intact equations and section structure.

Can I use marker_single to extract math equations from an arXiv PDF into Markdown?

Yes, marker_single extracts math equations from arXiv PDFs and converts them into Markdown while retaining LaTeX fidelity, making the content searchable and easy to edit in an Obsidian research vault.

What are the requirements to convert PDF documents to Markdown using marker_single?

Converting PDF documents to Markdown requires Python 3.10+ runtime and the marker_single CLI available on PATH, with configurable timeout settings and an option to preserve temporary output files.

Does marker_single retain the original section structure when converting academic papers to Markdown?

Yes, marker_single retains the original section structure when converting academic papers, ensuring that headings, paragraphs, and document hierarchy are preserved in the resulting Markdown output.

What is the best way to extract technical reports from PDF into editable Markdown for Obsidian?

The best way to extract technical reports into editable Markdown for Obsidian is using a Python API wrapper around marker_single, which preserves LaTeX math and document structure during the PDF conversion process.

Are there limitations when converting PDFs to Markdown with marker_single?

Limitations of converting PDFs with marker_single include dependency on a Python 3.10+ runtime and the CLI being available on PATH, while complex PDF layouts may require configurable timeout adjustments to process successfully.