iiif-digital-collections

What problem does it solve?

IIIF collections are published through standardized APIs, but turning manifests into usable images and scholarly text still requires careful parsing and request choreography. This Skill helps you reliably decode IIIF Presentation and Image APIs to retrieve canvases, specific image regions, and W3C Web Annotations for cross-institution research.

Core Features & Use Cases

• IIIF manifest parsing (v2/v3): Fetch and extract core metadata like title, creator, date, rights, description, and canvas counts from Presentation API manifests.
• IIIF image region download: Build Image API URLs and download full images or spatial regions for close analysis and citation-ready crops.
• Annotation extraction (W3C Web Annotations): Identify and extract non-painting scholarly annotations, including transcriptions, tags, descriptions, motivations, selectors, and body text.
• Cross-institution workflows: Compare and search across institutions by querying manifest endpoints and filtering by metadata terms.

Quick Start

Use the Skill to download an IIIF manifest, extract its canvas image service URLs, and then retrieve a specific region as an image for analysis.