skills.rest
Ming-Kai-LC
Ming-Kai-LCCOMMUNITY
Explore all skills by this author →
GitHub

pdf-processing

Split oversized PDFs into chunks and extract text and tables.

Updated Aug 23, 2026
Search Tags:#automation#ocr#document processing#data extraction#pdf#chunking#large files
Ready to run
npx skills add https://github.com/Ming-Kai-LC/python-projects-portfolio --skill pdf-processing
💬 Prompt for ChatGPT / Claude Chat▼
Please help me install this Agent Skill.
Skill: pdf-processing
Source: https://github.com/Ming-Kai-LC/python-projects-portfolio/tree/main/.claude/skills/pdf-processing
Command: npx skills add https://github.com/Ming-Kai-LC/python-projects-portfolio --skill pdf-processing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, PyMuPDF, pdfplumber, pdf2image, pytesseract, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Claude Code often struggles with large or complex PDF files, leading to crashes and lost context. This skill provides robust strategies and tools to reliably process any PDF, overcoming size limitations and ensuring seamless data extraction and analysis.

Core Features & Use Cases

  • Large PDF Handling: Splits oversized PDFs into manageable chunks to prevent AI crashes.
  • Advanced Extraction: Extracts text, tables, and even performs OCR on scanned documents with high accuracy.
  • Use Case: You have a 200-page financial report in PDF format that Claude Code can't read directly. Use this skill to chunk the PDF, extract all tables into CSVs, and get a full text summary, ready for analysis.

Quick Start

Process the large PDF 'annual_report.pdf' by splitting it into 25-page chunks, and then extract all text from the first chunk.