skills.rest
zfy465914233
zfy465914233COMMUNITY
Explore all skills by this author →
GitHub

extract-paper-images

Extract high-quality figures from arXiv sources or PDFs with filtering.

9|2|Updated Apr 2, 2026
Search Tags:#pdf#research#images#extract#arxiv#figures
One-click install
npx skills add https://github.com/zfy465914233/scholar-agent --skill extract-paper-images-zfy465914233
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract-paper-images
Source: https://github.com/zfy465914233/scholar-agent/tree/main/skills/extract-paper-images
Command: npx skills add https://github.com/zfy465914233/scholar-agent --skill extract-paper-images-zfy465914233

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill automates extracting high-quality figures from research papers by preferentially pulling images from arXiv source packages, reducing noise from logos and iconography and organizing outputs for note-taking.

Core Features & Use Cases

  • Prioritized arXiv source extraction: locate and copy genuine figures from typical image directories like pics/, figures/, figs/, images/, or root image files, then fall back to extracting figures from embedded PDFs when necessary.
  • PDF-based extraction as fallback: robustly extract images from PDFs when arXiv sources are unavailable or incomplete, with filtering to remove small logos and decorative elements.
  • Structured output and indexing: save images to 20_Research/Papers/[领域]/[论文标题]/images/ and generate an index file detailing image sources, sizes, and formats for easy reuse in notes.
  • Automated quick-start workflow: a single command to process a paper by ID or local PDF, producing image assets and a reference index.

Quick Start

Provide an arXiv ID or a local PDF path and run the extractor to save all usable figures to the target images directory and generate an index.

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?▼

Extract high-quality figures from an arXiv paper by providing its arXiv ID; the tool prioritizes pulling genuine source images from directories like pics/ or figures/, falling back to PDF extraction if sources are unavailable.

What is the best way to extract architecture diagrams from a research PDF?▼

The best way to extract architecture diagrams from a research PDF uses a three-tier flow that pulls embedded figures via PyMuPDF while automatically filtering out small logos and decorative icons.

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

Yes, you can extract images from a local PDF file by providing its path instead of an arXiv ID, triggering the PDF-based extraction fallback to locate and save embedded figures.

How does the extraction process filter out unwanted logos and icons?▼

The extraction process filters unwanted logos and icons by applying size-based constraints during arXiv source retrieval and PDF-based extraction, ensuring only substantial usable figures remain.

How are extracted paper images organized for note-taking?▼

Extracted paper images are organized by saving them to a structured notes directory path and generating an index file that details image sources, sizes, and formats for easy reuse.

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
jrcjrccjrcjrcc
17

academic-plotting

Generate architecture diagrams with Gemini AI and data charts with matplotlib and seaborn.

Community
Advanced
mindmorassmindmorass
2

pdf-harvester

Extract text, tables, and metadata from PDFs for RAG pipelines.

Community
Advanced
u9401066u9401066

pdf-reader

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

Community
Intermediate