pdf-figure-extract

Community

Extract figures from local PDFs efficiently.

Authorjimezsa
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Extract figures, architecture images, and diagrams from papers that are already downloaded locally, saving time hunting for visual content.

Core Features & Use Cases

  • Reuse existing PageIndex artifacts when available to narrow candidate pages.
  • Standalone PyMuPDF extraction when PageIndex artifacts are missing, ensuring no hard failures.
  • Export 1-3 high-quality figure candidates as PNGs with contextual captions and per-run manifests.

Quick Start

Extract the architecture figure from the local PDF and return the best match with page context.

Dependency Matrix

Required Modules

PyMuPDF

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: pdf-figure-extract
Download link: https://github.com/jimezsa/opencolab/archive/main.zip#pdf-figure-extract

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.