paper-processing

Parse academic papers to extract figures, references, and source files.

120|9|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/sodalone/paper-reading-skill --skill paper-processing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-processing
Source: https://github.com/sodalone/paper-reading-skill/tree/main
Command: npx skills add https://github.com/sodalone/paper-reading-skill --skill paper-processing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyPDF2, pymupdf, tarfile, latexparser, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables efficient handling, parsing, and organizing academic papers, reducing manual effort in research workflows.

Core Features & Use Cases

  • Automated Extraction: Retrieve titles, abstracts, figures, and references from PDFs and source archives.
  • Source Preparation: Organize source files, extract images, and parse LaTeX content for detailed analysis.
  • Use Case: A researcher wants to quickly prepare a review report by extracting figures, equations, and references from a collection of PDFs or arXiv sources, then organize them for deep analysis.

Quick Start

Use the paper-processing skill to pull all figures and references from your uploaded paper file, then organize the source files automatically.

Frequently Asked Questions about paper-processing

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

FAQPage Schema
How do I extract figures and references from academic PDFs?

To extract figures and references from academic PDFs, this Skill automates the retrieval of titles, abstracts, visual assets, and citation data using PyPDF2 and pymupdf. It systematically parses document structures to organize extracted content for research workflows.

Can I parse LaTeX source files from an arXiv tar archive?

Yes, you can parse LaTeX source files from an arXiv tar archive. The Skill uses the tarfile library to unpack source archives and latexparser to process LaTeX content, enabling detailed analysis of equations and document structure.

What is the best way to organize source files for a peer review report?

The best way to organize source files for a peer review report is through automated source preparation. This Skill extracts images, parses LaTeX content, and structures the extracted elements into a systematically organized format for deep analysis.

Does this PDF processing approach work with arXiv source files?

Yes, this PDF processing approach works with arXiv source files. It comprehensively handles both PDF documents and LaTeX source archives, extracting figures, equations, and references to support systematic academic paper analysis.

Do I need Python libraries to extract abstracts and titles from academic papers?

Yes, you need Python libraries like PyPDF2 and pymupdf to extract abstracts and titles from academic papers. These dependencies are required to automate the parsing tasks and manage the extraction of content from PDF files.