skills.rest
wangzr040220
wangzr040220COMMUNITY
Explore all skills by this author →
GitHub

extract-paper-images

Extract paper images from arXiv source packs with PDF fallback.

6|Updated Mar 6, 2026
Search Tags:#automation#workflow#pdf#arxiv#image-extraction#note-integration#paper-images
One-click install
npx skills add https://github.com/wangzr040220/claude-article-read --skill extract-paper-images
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract-paper-images
Source: https://github.com/wangzr040220/claude-article-read/tree/main/extract-paper-images
Command: npx skills add https://github.com/wangzr040220/claude-article-read --skill extract-paper-images

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

从论文中提取高质量图片，优先获取 arXiv 源码包中的原始论文图片，避免 PDF 中的商标、Logo 等非核心图片。

Core Features & Use Cases

  • ArXiv-source-first extraction: 优先从 arXiv 源码包中的 pics/、figures/、images/、img/ 目录提取高分辨率图片。
  • PDF fallback: 如源码包不可用，回退到从论文 PDF 中提取图片。
  • Indexing and Output: 将图片保存到 20_Research/Papers/[领域]/[论文标题]/images/ 目录，并生成图片索引 index.md。

Quick Start

运行脚本以对指定论文执行图片提取并生成图片索引。

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 images from an arXiv paper?▼

Extracting high-quality images from an arXiv paper is done by prioritizing the arXiv source pack to retrieve original high-resolution figures from directories like pics/ or figures/, avoiding non-core PDF images like logos.

Can I extract paper images from a PDF if the arXiv source is unavailable?▼

Yes, you can extract paper images from a PDF using a fallback extraction strategy powered by PyMuPDF when the arXiv source pack is inaccessible or unavailable for the target paper.

How do I organize extracted paper images and generate an index for notes?▼

Organize extracted paper images by saving them to a structured directory like 20_Research/Papers/[领域]/[论文标题]/images/, then automatically generate an index.md file to integrate the images into your notes.

Does this image extraction workflow handle errors when processing arXiv sources?▼

Yes, the image extraction workflow includes end-to-end error handling and fallback strategies, ensuring successful image acquisition even if issues arise during arXiv source pack downloading or PDF processing.

Do I need PyMuPDF to extract figures from arXiv source packs?▼

PyMuPDF is required for the PDF fallback extraction step to parse and extract images directly from the PDF file when the arXiv source pack is not available for figure retrieval.

Related Skills

Explore More Education & Research Skills→
u9401066u9401066

pdf-reader

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

Community
Intermediate
flashpoint493flashpoint493
1

paper-reading

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

Community
Advanced
ezjonlineezjonline
1

literature-research

Search PubMed and compile structured evidence reviews from scholarly sources.

Community
Advanced
exactlyexactly
24

composition-patterns

Implement scalable React UI with compound components and shared context.

Official
Intermediate