pdf

Extract text, tables, and images from PDF documents using Python libraries.

40|9|Updated Mar 23, 2025
One-click install
npx skills add https://github.com/kyopark2014/mcp --skill pdf-kyopark2014
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/kyopark2014/mcp/tree/main/application/skills/pdf
Command: npx skills add https://github.com/kyopark2014/mcp --skill pdf-kyopark2014

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab.

What problem does it solve?

PDF handling often requires repetitive, manual steps to extract text and tables, merge documents, rotate pages, fill forms, and apply OCR; this skill centralizes these operations into a single, reusable workflow.

Core Features & Use Cases

  • Text and table extraction from PDFs into structured data.
  • Merging, splitting, rotating pages, and editing PDFs.
  • Form filling, encryption/decryption, and OCR for scanned documents.
  • Use Case: automating invoice processing by extracting totals, dates, and vendor names from large sets of PDFs.

Quick Start

Submit a PDF file and ask to extract all text and tables.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and tables from PDF documents?

To extract text and tables from PDF documents, you can use Python libraries like pypdf and pdfplumber to parse binary streams into structured data. This skill automates that process, pulling text, tables, and images from PDF files for administrative and reporting workflows.

Can I merge, split, and edit PDFs programmatically using Python?

Yes, you can merge, split, rotate, and edit PDFs programmatically using Python libraries such as pypdf and reportlab. This skill centralizes these document operations into a single workflow, allowing you to transform and consolidate PDF archives without manual steps.

Does pdfplumber support OCR for scanned PDF files?

Yes, this skill applies OCR for scanned PDF files alongside pdfplumber and pypdf. It handles font embedding and non-Latin text extraction, allowing you to process and extract data from scanned documents that standard text extraction cannot parse.

What is the best way to automate invoice processing from large sets of PDFs?

The best way to automate invoice processing from large sets of PDFs is using a Python skill that extracts totals, dates, and vendor names into structured data. This tool uses pypdf and pdfplumber to parse binary streams and consolidate invoice data automatically.

How do I generate new PDFs and fill forms with reportlab?

You can generate new PDFs and fill forms using reportlab and pypdf within this skill. It handles font embedding and non-Latin text while creating new documents or filling existing forms, satisfying requirements for automated report generation and archival workflows.

Can I encrypt and decrypt PDF files using pypdf?

Yes, you can encrypt and decrypt PDF files using pypdf as part of this skill's workflow. It handles document security alongside merging, splitting, and editing operations, allowing you to secure sensitive PDF data during archival and consolidation processes.