digital-archive

Automate AI-enriched digital archives with integrated knowledge graphs from OCR, web, and social data.

359|61|Updated Dec 25, 2025

Search Tags:#multi-source #archive #knowledge-graph #entity-extraction #ai-enrichment #export-pipelines

Ready to run

npx skills add https://github.com/jamditis/claude-skills-journalism --skill digital-archive

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: digital-archive
Source: https://github.com/jamditis/claude-skills-journalism/tree/main/digital-archive
Command: npx skills add https://github.com/jamditis/claude-skills-journalism --skill digital-archive

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Building AI-enhanced digital archives from multi-source content, unifying data sources into a searchable knowledge base and structured archive.

Core Features & Use Cases

AI enrichment and knowledge graph construction to connect entities across articles, transcripts, and OCR'd content.
Multi-source ingestion, normalization, and unified schema mapping to produce consistent archives.
Entity extraction and relationship mapping to enable advanced search, recommendations, and provenance tracking.
PDF archival generation and accessible exports for long-term preservation and sharing.
Validation, quality checks, and export pipelines feeding frontend systems and data stores.

Quick Start

Start by feeding a dataset of sources (OCR'd newspapers, web articles, and transcripts) into the digital-archive workflow to generate an AI-enriched archive with a linked knowledge graph.

Frequently Asked Questions about digital-archive

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a knowledge graph from multi-source content like OCR text and web articles?▼

To build a knowledge graph from multi-source content, you ingest OCR text, web articles, and transcripts into a unified pipeline. The workflow applies AI entity extraction and relationship mapping to connect data points across your archives.

Can I use AI enrichment to extract entities and relationships from archived newspapers?▼

Yes, AI enrichment extracts entities and maps relationships from archived newspapers. This process applies Gemini AI to OCR'd content, linking people, places, and events across your digital archive for advanced search capabilities.

How do I normalize multi-source data into a unified schema for a digital archive?▼

You normalize multi-source data into a unified schema through automated ingestion pipelines. The workflow maps diverse inputs like web articles and transcripts into a consistent structure, enabling integrated digital archive generation.

What is the best way to generate PDF archives and export-ready outputs from structured data?▼

The best way to generate PDF archives and export-ready outputs is through dedicated export pipelines. After AI enrichment and validation, the system produces accessible PDF formats for long-term preservation and feeds frontend data stores.

Do I need Gemini AI to perform entity extraction and relationship mapping for my archive?▼

Yes, Gemini AI is required to perform entity extraction and relationship mapping. It drives the AI enrichment process that connects entities across articles, transcripts, and OCR'd content within the knowledge graph architecture.

Does this digital archive approach work for researchers needing provenance tracking across transcripts?▼

Yes, this digital archive approach works for researchers needing provenance tracking across transcripts. Entity extraction and relationship mapping enable advanced search, recommendations, and provenance tracking across integrated multi-source content.