ingesting-academic-content

Community

Ingest academic content into structured metadata.

Authorpelchers
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Academic content comes in many formats and from diverse sources, and researchers often struggle to unify metadata, structure, and citations for analysis and reuse.

Core Features & Use Cases

  • Multi-format ingestion: PDFs, DOCX, Markdown, HTML, and web pages.
  • Metadata and structure extraction: titles, authors, dates, keywords, chapters, sections, and references.
  • Citations and concept extraction: bibliographies, in-text citations, key concepts, and document classification (textbook, paper, lecture notes, assignment).

Quick Start

Ingest a sample PDF or DOCX academic document to produce a structured JSON containing metadata, outline, and extracted citations.

Dependency Matrix

Required Modules

pdf-parsepdf2pictesseract.jsnode-fetchjsdom@mozilla/readability

Components

Standard package

💻 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: ingesting-academic-content
Download link: https://github.com/pelchers/SessionSaver/archive/main.zip#ingesting-academic-content

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.