Image URL Extraction Skill

Official

Extract direct image URLs from archive pages.

AuthorEsyResearch
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill reliably retrieves direct image URLs from archive HTML pages (e.g., Wikimedia Commons, LOC, Smithsonian, Met, NARA) to prevent broken images in visual essays and downstream workflows.

Core Features & Use Cases

  • Deterministic extraction: Uses source-specific reference files to locate the actual image URL from archive pages.
  • Source coverage: Supports Wikimedia Commons, Library of Congress, Smithsonian, Metropolitan Museum of Art, National Archives, and a generic fallback path for unknown sources.
  • Verification & reliability: Includes URL verification and content-type checks to ensure the URL resolves to an image, not HTML.
  • Operational integration: Designed to be invoked by image curation agents and to feed directly into embedding or download workflows.

Quick Start

Identify the source by URL pattern, open the corresponding reference file, run the extraction per that reference, verify the extracted URL is an image, and then use it as the direct image URL.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: Image URL Extraction Skill
Download link: https://github.com/EsyResearch/home.esy.com/archive/main.zip#image-url-extraction-skill

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 223,000+ vetted skills library on demand.