[IMPORTANT] Use

TaskCreate

to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.

Quick Summary

1. Auto-Detect — Determine if PDF has native text or needs OCR
2. Convert — Run

   scripts/convert.cjs

   with input path and optional mode/output flags
3. Output — Returns JSON with success status, page count, and output path

• Use

  --mode auto

  (default) to let the tool decide native vs OCR
• OCR for scanned PDFs requires additional

  tesseract.js

  setup
• Complex multi-column layouts may not preserve structure perfectly

pdf-to-markdown

No npm install required

node_modules

@opendocsg/pdf2md

npm install

npx

Quick Start

# Basic conversion (auto-detect native vs scanned)
node .agents/skills/pdf-to-markdown/scripts/convert.cjs --input ./document.pdf

# Specify output path
node .agents/skills/pdf-to-markdown/scripts/convert.cjs -i ./doc.pdf -o ./output.md

# Force native mode (skip OCR detection)
node .agents/skills/pdf-to-markdown/scripts/convert.cjs -i ./doc.pdf --mode native

CLI Options

--input

-i

--output

-o

{input}.md

--mode

-m

auto

native

ocr

auto

--help

-h

Features

• Auto-Detection: Automatically determines if PDF has native text or requires OCR
• Native PDFs: Fast extraction using @opendocsg/pdf2md
• Tables: Basic table structure preservation
• Cross-Platform: Works on Windows, macOS, Linux
• No System Dependencies: Pure JavaScript implementation

Conversion Modes

Auto (Default)

Native

OCR (Scanned PDFs) - Coming Soon

Output

{
    "success": true,
    "input": "/path/to/input.pdf",
    "output": "/path/to/output.md",
    "stats": {
        "pages": 5,
        "mode": "native"
    }
}

Limitations

• Complex multi-column layouts may not preserve structure
• Scanned PDF OCR accuracy depends on image quality
• Mathematical formulas may not convert perfectly
• First-run OCR downloads language data (~15MB)

OCR Setup (Optional)

cd .agents/skills/pdf-to-markdown
npm install tesseract.js pdfjs-dist canvas

canvas

• Always plan and break work into many small todo tasks
• Always add a final review todo task to verify work quality and identify fixes/enhancements