read-paper

Download arXiv papers and convert them into Obsidian-ready Markdown reports.

Updated Apr 21, 2026

Search Tags:#Obsidian #OCR #Markdown #arXiv #paper parsing

Ready to run

npx skills add https://github.com/LuYanFCP/common-skills --skill read-paper-luyanfcp

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: read-paper
Source: https://github.com/LuYanFCP/common-skills/tree/main/read-paper
Command: npx skills add https://github.com/LuYanFCP/common-skills --skill read-paper-luyanfcp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires use-ocr, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of downloading, parsing, and converting arXiv papers into Obsidian-ready Markdown reports, saving time and streamlining research workflows.

Core Features & Use Cases

Automated Paper Downloading: Automatically download papers from arXiv based on provided arXiv ID or URL.
PDF Parsing: Extract text, tables, formulas, and handwriting from PDFs using local OCR.
Markdown Report Generation: Generate Obsidian Markdown reports with frontmatter metadata and copied figure assets.
Use Case: When you need to quickly create a research note for an arXiv paper in Obsidian, this skill can help you by automating the process of downloading, parsing, and formatting the paper.

Quick Start

Use the read-paper skill to generate a report for the arXiv paper with ID '2503.01840'.

Frequently Asked Questions about read-paper

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

FAQPage Schema

How do I convert arXiv papers to Markdown for Obsidian?▼

Converting arXiv papers to Markdown for Obsidian is done by automating the download, OCR parsing, and formatting processes to generate reports with frontmatter metadata and copied figure assets.

What is the best way to extract text and tables from an arXiv PDF?▼

Extracting text and tables from an arXiv PDF is best handled by automated OCR parsing, which also extracts formulas and figures to create a structured Markdown report.

Do I need a local OCR setup and Python environment to parse PDFs?▼

Yes, a local OCR setup and Python environment are required to parse PDFs, as the automated paper parsing and Markdown conversion process relies on these local dependencies.

How does automated paper parsing handle figures and formulas from PDFs?▼

Automated paper parsing handles figures and formulas by using local OCR to extract them from the PDF, copying figure assets, and embedding the extracted content into an Obsidian-ready Markdown report.

Can I automatically download arXiv papers using an arXiv ID?▼

Yes, you can automatically download arXiv papers by providing the specific arXiv ID or URL, which the workflow then uses to fetch and parse the document.

What are the limitations of using local OCR for paper parsing?▼

Limitations of using local OCR for paper parsing include the requirement for a local Python environment and OCR setup, which may struggle with complex handwriting or poorly scanned PDFs.