paper-deep-read

Convert scholarly PDFs into structured Obsidian notes with YAML frontmatter.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Elephenman/paper-deep-read --skill paper-deep-read
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-deep-read
Source: https://github.com/Elephenman/paper-deep-read/tree/main
Command: npx skills add https://github.com/Elephenman/paper-deep-read --skill paper-deep-read

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Paper Deep Read automates the extraction and interpretation of scientific literature, turning PDFs into structured Obsidian notes with cross-paper links, YAML frontmatter, and a scalable knowledge graph workflow.

Core Features & Use Cases

  • Full-text visual extraction: figures, tables, and formulas from PDFs.
  • Obsidian-native outputs: YAML frontmatter, backlinks, tags, Callout blocks, and Dataview-friendly structure.
  • 6-phase execution pipeline with batch processing, QA, and knowledge-graph construction across multiple papers.
  • Knowledge management: automatic PaperVault organization, MOC updates, and cross-paper concept linking.
  • Use case: researchers batch-read dozens of papers, produce standardized notes, and build a literature knowledge graph.

Quick Start

Feed a PDF to Paper Deep Read to generate a complete Obsidian note in PaperVault.

Frequently Asked Questions about paper-deep-read

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

FAQPage Schema
How do I convert scholarly PDFs into structured Obsidian notes with YAML frontmatter?

To convert scholarly PDFs into structured Obsidian notes, this Skill applies a six-phase pipeline to extract text, figures, and tables, outputting Markdown files with YAML frontmatter, backlinks, and Dataview-ready structures directly into your PaperVault.

Can I batch process multiple academic papers to build an Obsidian knowledge graph?

Yes, you can batch process multiple academic papers to build an Obsidian knowledge graph. The workflow executes QA loops and cross-paper concept linking, automatically organizing outputs into PaperVault and updating your Map of Content for scalable literature analysis.

How does PDF extraction handle complex figures, tables, and formulas for literature reviews?

PDF extraction for literature reviews uses PyMuPDF to capture full-text visual elements, isolating complex figures, tables, and formulas. This ensures reproducible analysis by preserving the structural and visual integrity of the original scholarly document within the generated notes.

Do I need PyMuPDF installed to extract full-text and metadata from research papers?

Yes, you need PyMuPDF installed as a dependency to extract full-text and metadata from research papers. It provides the core PDF parsing capabilities required to identify visual elements and structure the extracted content into Obsidian-ready Markdown files.

What is the best way to create cross-paper links for a reproducible literature review in Obsidian?

The best way to create cross-paper links for a reproducible literature review is using an automated six-phase processing pipeline. It maps concepts across documents, standardizes metadata in YAML, and generates backlinks to construct a scalable, interconnected knowledge graph.