pdf

Extract text, tables, images, and metadata from PDF documents.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/rizaldiem/digital-invitation-web_V2 --skill pdf-rizaldiem
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/rizaldiem/digital-invitation-web_V2/tree/main/.windsurf/skills/pdf
Command: npx skills add https://github.com/rizaldiem/digital-invitation-web_V2 --skill pdf-rizaldiem

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manual handling of PDFs—reading, extracting structured data, filling forms, merging, splitting, applying OCR, and annotating—is time consuming and error prone; this skill centralizes reliable, repeatable PDF workflows so you can process documents at scale with fewer mistakes.

Core Features & Use Cases

  • Text and Table Extraction: Extract plain text, layout-preserving text, and structured tables from born-digital and scanned PDFs.
  • Form Handling & Filling: Detect fillable fields, extract field metadata, or place annotations on non-fillable forms with coordinate conversion helpers.
  • Manipulation and Utilities: Merge/split/rotate pages, add watermarks, extract images, perform OCR, and encrypt/decrypt documents. Use case: batch-extract invoice data and populate a CSV or automatically fill standardized application PDFs.

Quick Start

Extract all text and tables from invoice-q3.pdf, run OCR if needed, and output a merged CSV with detected line items and totals.

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 programmatically?

You can extract text and tables from scanned PDFs by using pdfplumber for layout-preserving parsing and pdf2image with Pillow to run OCR. This approach detects structured line items and handles both born-digital and scanned documents accurately.

Can I automate filling standardized PDF forms and extracting field metadata?

Automating PDF form filling is supported by detecting fillable fields and extracting field metadata. For non-fillable forms, coordinate conversion helpers and bounding box validation place annotations accurately to populate standardized documents.

Does this PDF processing approach work with password-protected files?

Yes, PDF processing works with password-protected files. It supports encrypting and decrypting documents, allowing you to merge, split, rotate pages, and add watermarks while maintaining secure access controls.

What is the best way to batch extract invoice data from PDFs into a CSV?

The best way to batch extract invoice data into a CSV is to use pypdf and pdfplumber to parse text and tables, running OCR on scanned pages if needed. This yields a merged CSV with detected line items and totals.

How do I merge, split, and watermark PDF documents without manual editing?

You can merge, split, rotate, and watermark PDF documents programmatically using pypdf. This centralizes reliable, repeatable workflows to process documents at scale with fewer manual errors.

When should I use pdfplumber instead of pypdf for PDF text extraction?

Use pdfplumber for layout-preserving text and structured table parsing, while pypdf handles general manipulation like merging, splitting, and encryption. Combining both ensures accurate extraction across born-digital and scanned PDFs.