skills.rest
changtaoli
changtaoliCOMMUNITY
Explore all skills by this author →
GitHub

extract-paper-images

Extract high-quality figures from arXiv sources or local PDFs.

4|Updated Apr 11, 2026
Search Tags:#arxiv#pdf-processing#research-notes#image-extraction#paper-images#source-packages
One-click install
npx skills add https://github.com/changtaoli/claude-paper-skills --skill extract-paper-images-changtaoli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract-paper-images
Source: https://github.com/changtaoli/claude-paper-skills/tree/main/skills/extract-paper-images
Command: npx skills add https://github.com/changtaoli/claude-paper-skills --skill extract-paper-images-changtaoli

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill automates the extraction of images from academic papers, prioritizing true figures from arXiv source packages over embedded logos to enrich notes and references.

Core Features & Use Cases

  • Priority image extraction from arXiv source (pics/figures) to obtain high-quality, publication-ready figures.
  • Fallback image extraction from PDFs to ensure images are captured when sources are unavailable.
  • Generates an index and saves images under 资源/论文图片/[论文标题]/ for easy reuse in notes.

Quick Start

Run the extractor with an arXiv ID or local PDF path to automatically download sources when available, extract high-quality figures (prioritizing arXiv source images), and save them to 资源/论文图片/[论文标题]/ with an index for later reference.

Frequently Asked Questions about extract-paper-images

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

FAQPage Schema
How do I extract high-quality figures from an arXiv paper?▼

To extract figures from an arXiv paper, this skill downloads arXiv source packages to locate original publication-ready images, falling back to PDF extraction only when sources are unavailable. It outputs a structured index with file paths and metadata.

Can I extract images from a local PDF instead of an arXiv ID?▼

Yes, you can extract images from a local PDF. The skill accepts local PDF paths as input and applies fallback PDF processing to capture embedded figures when arXiv source packages are not available.

What is the best way to get publication-ready images from arXiv source packages?▼

The best way to get publication-ready images is prioritizing extraction from standard directories within arXiv source packages, which yields true source figures rather than downscaled embedded logos extracted directly from PDFs.

Does PyMuPDF support extracting multiple image formats and sizes from academic papers?▼

Yes, PyMuPDF supports extracting multiple image formats and sizes from academic papers. The skill leverages PyMuPDF to handle fallback PDF extraction when arXiv source packages are unavailable.

Why do extracted PDF figures look lower quality than original paper images?▼

Extracted PDF figures look lower quality because they are often embedded logos or downscaled versions. This skill prioritizes downloading arXiv source images to obtain true, high-quality paper figures instead.

Related Skills

Explore More Education & Research Skills→
OpenLAIROpenLAIR
1.0k

paper-image-extractor

Extract figures from academic papers using arXiv source packages or PDFs.

Official
Intermediate
flashpoint493flashpoint493
1

paper-reading

Download and analyze academic papers to generate structured notes and code.

Community
Advanced
u9401066u9401066

pdf-reader

Extract text, figures, and citations from PDFs into Markdown.

Community
Intermediate
vigneshksaithalvigneshksaithal

adapt

Adapt existing designs across mobile, tablet, desktop, print, and email contexts.

Community
Advanced