pdf

Extract and manipulate PDF content including text, tables, images, annotations and form fields.

Updated Mar 6, 2026

Search Tags:#automation #ocr #pdf #pypdf #data-extraction #form-filling

Ready to run

npx skills add https://github.com/pczhao1210/reuseable-agents-and-skills --skill pdf-pczhao1210

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/pczhao1210/reuseable-agents-and-skills/tree/main/.agents/skills/pdf
Command: npx skills add https://github.com/pczhao1210/reuseable-agents-and-skills --skill pdf-pczhao1210

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Eliminates manual, error-prone work with PDFs by providing reliable tools to extract text and tables, fill forms (fillable and non-fillable), merge/split documents, apply OCR to scanned pages, and produce annotated or password-protected outputs.

Core Features & Use Cases

Automated Form Filling: Fill interactive form fields or place text annotations into non-fillable forms using coordinate-aware workflows.
Extraction & OCR: Extract plain text, structured tables, and images from PDFs and run OCR on scanned documents to make them searchable.
Document Manipulation: Merge, split, rotate, watermark, encrypt/decrypt, and batch-process PDFs for invoices, reports, or archival conversion.

Quick Start

Use the pdf skill to extract all text and tables from invoice-q3.pdf and output them as a combined CSV file.

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 and export them to CSV?▼

To extract text and tables from PDFs, use pdfplumber to isolate page elements and output structured data as a combined CSV file. This approach reliably captures plain text and structured tabular data for batch invoice or report processing.

Can I automate filling non-fillable PDF forms using coordinate-aware workflows?▼

Yes, you can automate filling non-fillable PDF forms by placing text annotations using coordinate-aware workflows. This process validates coordinates to accurately position text on scanned pages or static documents without interactive form fields.

Does pdfplumber support OCR for scanned PDF pages to make them searchable?▼

Yes, pdfplumber supports OCR integration for scanned PDF pages to make them searchable. By rendering pages with pdf2image and processing them with Pillow, you can extract text from scanned documents and produce searchable outputs.

What is the best way to batch process and merge multiple PDF files for archival conversion?▼

The best way to batch process and merge multiple PDFs for archival conversion is using pypdf to combine documents programmatically. This method supports merging, splitting, and batch-processing invoices or reports into a single output.

Why does PDF table extraction return misaligned data when processing scanned invoices?▼

PDF table extraction returns misaligned data for scanned invoices because the document lacks embedded text layers. Applying OCR to the scanned pages first resolves this by generating searchable text before attempting structured table extraction.

Do I need Python and command-line tooling to manipulate PDFs and apply watermarks or encryption?▼

Yes, you need Python and command-line tooling integration to manipulate PDFs and apply watermarks or encryption. Libraries such as pypdf, pdfplumber, pdf2image, and Pillow are required to render pages, validate coordinates, and produce annotated or password-protected outputs.