pdf

Convert PDF documents into extracted text, tables, images, and editable outputs.

28|5|Updated Jun 24, 2025
One-click install
npx skills add https://github.com/thevibeworks/claude-code-docs --skill pdf-thevibeworks
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/thevibeworks/claude-code-docs/tree/main/content/github/skills/skills/pdf
Command: npx skills add https://github.com/thevibeworks/claude-code-docs --skill pdf-thevibeworks

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates manual, error-prone PDF handling by automating extraction, transformation, and form completion so you can work with PDFs as usable data instead of static files.

Core Features & Use Cases

  • PDF text and table extraction: Extract readable text and structured tables (including layout-aware text) for analysis or downstream processing.
  • End-to-end PDF editing workflows: Merge, split, rotate pages, add watermarks, encrypt/decrypt, and extract embedded images.
  • OCR for scanned documents: Convert scanned PDFs into searchable text using a standard OCR flow.
  • Form handling guidance: Provides a step-by-step process to detect fillable fields, compute field bounding boxes, validate them, and fill the form with annotations when needed.

Use Case Example: You receive a scanned multi-page PDF application with mixed text and checkboxes—use this Skill to OCR it, extract the relevant fields, and produce a correctly filled output PDF.

Quick Start

Ask Claude to fill out a provided PDF form by extracting fillable fields, preparing field coordinates, validating bounding boxes, and generating the filled PDF output.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract tables and text from a PDF using Python?

PDF table and text extraction can be automated using Python tooling like pdfplumber and pypdf to pull readable text and structured tables from documents for downstream analysis.

Can I use Python to fill out PDF forms automatically?

PDF form filling in Python involves detecting fillable fields, computing bounding box coordinates, validating them, and generating a filled output PDF using libraries like pypdf and reportlab.

What's the best way to OCR a scanned PDF and make it searchable?

OCR for scanned PDFs converts static images into searchable text by applying standard OCR utilities and command-line tools, transforming scanned documents into usable text data.

How do I merge, split, and rotate PDF pages without manual editing?

Merging, splitting, and rotating PDF pages is handled through command-line utilities like qpdf and Python libraries, automating document transformation workflows without manual intervention.

Does extracting embedded images from PDFs require special dependencies?

Extracting embedded images from PDFs requires command-line utilities like pdfimages and Python tooling, which pull visual assets out of static documents for separate processing.

How do I add watermarks and encrypt PDF files programmatically?

Watermarking and encrypting PDF files programmatically is achieved using Python libraries like pypdf and reportlab, applying security overlays and encryption to protect document contents.