pdf

Extract text, bounding boxes, and form fields from PDF documents.

Updated Aug 23, 2026

Search Tags:#automation #document processing #data extraction #pdf #validation #form filling #Python

One-click install

npx skills add https://github.com/hanthienduc/myprotocol-stack --skill pdf-hanthienduc

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/hanthienduc/myprotocol-stack/tree/main/.claude/skills/document-skills/pdf
Command: npx skills add https://github.com/hanthienduc/myprotocol-stack --skill pdf-hanthienduc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually handling PDF documents for form filling, data extraction, or validation is a time-consuming and error-prone process. This skill provides a suite of Python scripts to automate these tasks, transforming static PDFs into dynamic, actionable data sources.

Core Features & Use Cases

Automated Form Filling: Programmatically fill both fillable and non-fillable PDF forms, including complex layouts with annotations.
Precise Data Extraction: Extract text, bounding box information, and form field details from any PDF, enabling structured data capture.
Visual Validation: Generate validation images to visually confirm the accuracy of filled fields and extracted data, ensuring high fidelity.
Use Case: You receive hundreds of standardized application forms as PDFs. Use this skill to automatically extract applicant names, addresses, and other key information, then fill out a summary PDF with the extracted data, all without manual intervention.

Quick Start

Use the pdf skill to extract all text from the attached file 'invoice-q3.pdf'.