pdf

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

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/ian-pascoe/dotfiles-chezmoi --skill pdf-ian-pascoe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/ian-pascoe/dotfiles-chezmoi/tree/main/dot_agents/skills/pdf
Command: npx skills add https://github.com/ian-pascoe/dotfiles-chezmoi --skill pdf-ian-pascoe

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The PDF skill removes the manual friction of reading, reorganizing, and completing PDF documents. It helps turn static or scanned PDFs into usable text, structured data, and finished files without repetitive hand editing.

Core Features & Use Cases

  • Text and table extraction: Pull text, tables, and metadata from PDFs for analysis or reuse.
  • PDF transformation: Merge, split, rotate, watermark, encrypt, decrypt, and create PDFs programmatically.
  • Form handling: Fill fillable forms directly and use coordinate-based annotations for non-fillable forms.
  • OCR support: Convert scanned PDFs into searchable text when the document is image-based.
  • Example use case: Process invoices, applications, or reports by extracting their contents, populating fields, and exporting a clean final document.

Quick Start

Use the pdf skill to extract the text from the attached PDF and tell me if it is fillable, scanned, or needs form-field annotations.

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 a PDF document?

To extract text and tables from a PDF, you need Python tooling to inspect the document structure and pull content. This process converts static PDF data into usable text and structured table formats for analysis or reuse.

Can I fill out both fillable and scanned PDF forms?

Yes, you can fill fillable PDF forms directly and use coordinate-based annotations for non-fillable or scanned files. This requires rendering pages and validating coordinates to write transformed output reliably.

How do I run OCR on a scanned PDF to make it searchable?

Running OCR on a scanned PDF converts image-based documents into searchable text. This requires rendering PDF pages as images using libraries like pdf2image and Pillow before applying text recognition.

What's the best way to merge, split, and watermark PDF files programmatically?

The best way to merge, split, or watermark PDF files programmatically is using Python PDF tooling. These libraries allow you to manipulate document structures, apply transformations, and write reliable output files.

Does this PDF processing approach work with encrypted documents?

Yes, this approach handles encrypted documents by applying encryption and decryption transformations. It inspects the PDF structure to validate access permissions before extracting text or writing modified output.

Why do I need multiple Python PDF libraries to extract text and images?

Multiple Python libraries are needed because PDF processing requires rendering pages, inspecting structure, and writing output. Tools like pypdf, pdfplumber, pdf2image, and Pillow each handle specific extraction and transformation tasks reliably.