PDF Reader Skill

Extract and process content from PDF documents.

Basic Text Extraction

python3 -c "
import subprocess
result = subprocess.run(['pdftotext', '{file}', '-'], capture_output=True, text=True)
print(result.stdout[:5000])
"

Page-by-Page Extraction

python3 -c "
import subprocess
result = subprocess.run(['pdftotext', '-f', '{first_page}', '-l', '{last_page}', '{file}', '-'], capture_output=True, text=True)
print(result.stdout)
"

PDF Metadata

python3 -c "
import subprocess
result = subprocess.run(['pdfinfo', '{file}'], capture_output=True, text=True)
print(result.stdout)
"

Table Extraction

python3 -c "
import subprocess
result = subprocess.run(['pdftotext', '-layout', '{file}', '-'], capture_output=True, text=True)
print(result.stdout[:5000])
"

Guidelines

• Try pdftotext first — it's fast and handles most PDFs well
• Use -layout flag to preserve table formatting
• For scanned PDFs, note that OCR is needed (not supported by pdftotext)
• Extract specific page ranges for large documents
• Summarize extracted content rather than dumping entire documents