phd-deepread

Community

Turn PDFs into structured notes with AI insights.

Authorheleninsights-dot
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Researchers and power users often spend excessive time turning academic PDFs into actionable, Obsidian-ready literature notes. This skill automates extraction, AI-assisted note generation, and critical-thinking canvases to streamline systematic reviews and knowledge-building workflows.

Core Features & Use Cases

  • Text-First PDF Extraction: Uses PyMuPDF for fast text extraction with optional OCR fallback (Tesseract) for scanned or complex pages.
  • Structured Note Generation: Template-driven generation that produces YAML frontmatter notes compatible with Dataview and Obsidian.
  • Critical-Thinking Canvases: 9-node JSON Canvas outputs for deep, structured critique and reasoning.
  • Workflow Automation: End-to-end orchestration of extract → generate → canvas, including batch processing.

Quick Start

Run phd-deepread extract paper.pdf to produce markdown_output, then run generate and canvas to complete the workflow.

Dependency Matrix

Required Modules

PyMuPDFpytesseractPillow

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: phd-deepread
Download link: https://github.com/heleninsights-dot/phd-deepread-workflow/archive/main.zip#phd-deepread

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.