pdf

Extract and manipulate PDF content and metadata using Python libraries.

Updated Sep 26, 2025
One-click install
npx skills add https://github.com/zsutxz/AICodingWithBMad --skill pdf-zsutxz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/zsutxz/AICodingWithBMad/tree/main/.claude/skills/pdf
Command: npx skills add https://github.com/zsutxz/AICodingWithBMad --skill pdf-zsutxz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pytesseract, pdf2image, pypdfium2, pandas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Manually handling PDFs for data extraction, form filling, or document manipulation is a slow, error-prone process. This Skill eliminates tedious manual work by automating complex PDF operations, saving you hours of repetitive effort.

Core Features & Use Cases

  • Comprehensive PDF Manipulation: Extract text and structured table data, create new PDFs, merge, split, rotate, and password-protect documents.
  • Automated Form Filling: Programmatically fill both fillable and non-fillable PDF forms with high accuracy, converting bounding box coordinates for precise text placement.
  • OCR for Scanned Documents: Extract text from scanned PDFs using integrated OCR capabilities, making inaccessible content searchable and editable.
  • Use Case: Automatically extract all tables from a quarterly financial report PDF and convert them into an Excel spreadsheet for analysis, or fill out a stack of legal forms with client data from a database.

Quick Start

Extract all text and tables from the attached PDF document 'quarterly_report.pdf' and summarize the key findings.

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?

Extract text and tables from PDFs using libraries like pdfplumber and pypdf, which parse document structure and retrieve content in machine-readable formats. These tools handle both simple text extraction and complex table data recovery from multi-page documents.

Can I programmatically fill PDF forms with data?

Yes, programmatic form filling works by converting bounding box coordinates to precise text placement positions using pypdf and reportlab. This approach fills both fillable and non-fillable forms with high accuracy, enabling batch processing from external data sources.

How do I extract text from scanned or image-based PDFs?

Use OCR capabilities via pytesseract and pdf2image to convert scanned PDFs into searchable, editable text. These tools extract content from image-based documents that standard text extraction cannot access.

What PDF operations can I automate beyond text extraction?

Automate merging, splitting, rotating, password-protecting, and creating new PDFs. Libraries like pypdf and reportlab support these document manipulations, enabling scalable batch workflows for form-based and annotation-driven processes.

Do I need command-line tools or can I work purely in Python?

Python libraries (pypdf, pdfplumber, reportlab, pytesseract) handle most PDF tasks programmatically. Command-line tools complement these for specialized operations, but core extraction, form filling, and transformation work entirely within Python.

When should I use OCR versus standard text extraction on PDFs?

Use standard text extraction for born-digital PDFs with embedded text; OCR is necessary for scanned documents, images, or PDFs where text is rendered as graphical content, trading processing speed for accessibility of previously unreadable content.