pdf

Automate PDF text extraction, form filling, and batch processing with Python libraries.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/rapyuta-robotics/agent-ai --skill pdf-rapyuta-robotics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/rapyuta-robotics/agent-ai/tree/main/skills/pdf
Command: npx skills add https://github.com/rapyuta-robotics/agent-ai --skill pdf-rapyuta-robotics

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDF documents are pervasive in business, but extracting text, filling forms, and combining pages often requires manual, repetitive work. This Skill provides a code-first approach to automate common PDF tasks end-to-end.

Core Features & Use Cases

  • Automate text and table extraction from PDFs using Python libraries like pypdf and pdfplumber.
  • Fill out fillable forms and annotate non-fillable ones for automated workflows.
  • Batch process PDFs: merge, split, rotate, and annotate to scale document workflows.

Quick Start

Use the provided scripts to inspect and automate PDF tasks on sample PDFs:

  • Inspect form fields: python scripts/extract_form_field_info.py sample.pdf fields.json
  • Fill fields with JSON data: python scripts/fill_fillable_fields.py sample.pdf fields.json filled.pdf
  • Generate validation images for QA: python scripts/create_validation_image.py 1 fields.json sample-page1.png

Frequently Asked Questions about pdf

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

FAQPage Schema
How do I automate PDF text extraction using Python?

Automate PDF text extraction using Python by leveraging the pypdf library to parse document content. This Skill provides scripts to inspect, extract, and save text data from PDF files for automated document digitization and processing.

Can I fill out fillable PDF forms programmatically with Python?

Yes, you can fill fillable PDF forms programmatically by passing JSON data into the provided Python scripts. The Skill maps JSON key-value pairs to PDF form fields automatically, outputting a completed PDF document for batch form-filling workflows.

What's the best way to batch process PDFs for merging and splitting?

Batch process PDFs for merging and splitting by running Python scripts that utilize pypdf to manipulate document structures. This Skill automates scaling document workflows, allowing you to combine, split, or rotate multiple PDF files programmatically.

How do I render PDF pages to images for QA validation?

Render PDF pages to images for QA validation using the pdf2image and Pillow dependencies. The Skill includes scripts to generate PNG validation images from PDF pages, allowing visual inspection of filled form fields and document layouts.

Does this PDF processing approach work for both fillable and non-fillable forms?

Yes, this PDF processing approach handles both fillable and non-fillable forms. You can fill fillable fields with JSON data or annotate non-fillable PDFs, enabling automated form handling across various document types in engineering and admin workflows.

How do I inspect existing form fields in a PDF document?

Inspect existing form fields in a PDF document by running the extract_form_field_info.py script with pypdf. This parses the PDF structure and outputs a JSON file containing all detected field names and properties for automated form mapping.