pdf

Extract text, tables, and structured data from PDFs using Python libraries.

Updated May 9, 2026
One-click install
npx skills add https://github.com/kk20300113-png/my-claude-skills --skill pdf-kk20300113-png
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/kk20300113-png/my-claude-skills/tree/main/vibe/bundled/skills/document-skills/pdf
Command: npx skills add https://github.com/kk20300113-png/my-claude-skills --skill pdf-kk20300113-png

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill eliminates the tedious, time-consuming manual work of processing PDF documents, including extracting data from scanned files, merging multiple reports, and filling out repetitive forms one by one.

Core Features & Use Cases

  • Text and Table Extraction: Pull text and structured table data from both digital and scanned PDFs, converting them to editable formats like Excel or CSV.
  • PDF Creation and Manipulation: Merge, split, rotate, add watermarks to, or create new PDFs from scratch using Python libraries or command-line tools.
  • Form Automation: Fill both fillable and non-fillable PDF forms programmatically, with built-in validation to ensure data is placed in the correct locations.
  • Use Case: A finance team can use this skill to process 100 vendor invoices: extract invoice numbers, dates, and totals from each PDF, then compile the data into a single CSV file for accounting software.

Quick Start

Use the pdf skill to extract all text and tables from the attached file 'vendor_invoices.pdf' and save the extracted table data to an Excel spreadsheet.

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 scanned PDFs for data processing?

To extract text and tables from scanned PDFs, this skill applies optical character recognition to parse binary streams and convert structured data into editable formats. It uses pytesseract to digitize scanned files without manual intervention.

Can I automate filling out PDF forms programmatically without manual data entry?

Yes, you can automate filling out PDF forms programmatically. This skill places data into both fillable and non-fillable forms with built-in validation to ensure correct placement, eliminating repetitive manual entry.

What's the best way to merge and split multiple PDF reports for archival retrieval?

The best way to merge and split PDF reports is using this skill's manipulation features. It leverages pypdf to manipulate page content, allowing you to merge multiple reports or split documents for archival data retrieval.

Does this PDF extraction approach work with Python libraries like pypdf and pdfplumber?

Yes, this PDF extraction approach works directly with Python libraries including pypdf and pdfplumber. These dependencies parse binary PDF streams and manipulate page content to pull text and structured table data.

How do I convert extracted PDF invoice data into a CSV file for accounting software?

To convert extracted PDF invoice data into a CSV file, this skill pulls invoice numbers, dates, and totals from digital documents. It then compiles the extracted structured data into a single CSV file for accounting software.

Do I need optical character recognition to process administrative PDF workflows?

You need optical character recognition to process administrative PDF workflows if the files are scanned. This skill uses pytesseract to perform OCR on scanned documents, extracting text for form digitization and invoice processing.