phd-deepread

# PhD Deep Read Workflow This skill implements a sophisticated **PhD Deep Read Workflow** that processes academic PDFs into structured literature notes for Obsidian using a hybrid decision-tree approach. The workflow combines: 1. **Text-First PDF Extraction**: Decision-tree using PyMuPDF (fast text extraction) for searchable PDFs and Tesseract OCR fallback for scanned/complex pages 2. **Structured Note Generation**: Template-driven generation of comprehensive academic literature notes 3. **Critical Thinking Canvas**: JSON Canvas files with 9 interconnected nodes for deep critical analysis 4. **Workflow Automation**: Scripts to automate the 4-stage pipeline ## When to Use This Skill Activate when the user: - Wants to process academic PDFs into structured literature notes - Needs to extract text from PDFs with complex layouts or tables - Wants to generate Obsidian-compatible notes with YAML frontmatter and Dataview callouts - Needs critical thinking canvases for deep analysis of papers - Has a collection of PDFs to process in batch ## Commands The skill provides these main commands: - `setup`: Setup environment and install required tools (PyMuPDF, Tesseract OCR) - `extract`: Extract text and images from PDFs using Text-First decision tree (PyMuPDF + Tesseract OCR) - `generate`: Generate structured literature notes using .clauderules template - `canvas`: Create JSON Canvas files for critical thinking with 9 interconnected nodes - `run`: Run full workflow automation (extra...