One-click install
npx skills add https://github.com/shushuzn/Rairos --skill pdf-shushuzn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/shushuzn/Rairos/tree/main/skills/pdf
Command: npx skills add https://github.com/shushuzn/Rairos --skill pdf-shushuzn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow, pytesseract, pandas, reportlab, pdfjs-dist, pdf-lib, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the manual burden of working with PDF files by letting you extract content, transform layouts, and fill out forms (including scanned, image-based PDFs via OCR).

Core Features & Use Cases

  • Extract text and tables from PDFs (with layout-aware extraction and table extraction for structured data).
  • Edit and transform PDFs by merging, splitting, rotating pages, adding watermarks, encrypting/decrypting, and extracting images.
  • Fill PDF forms and annotations by detecting fillable fields, extracting field metadata, validating bounding boxes, and producing a filled output (or adding text annotations when fields are not fillable).

Use case: You receive a batch of scanned application forms as PDFs, extract the form fields, apply OCR where needed, and generate completed PDFs ready for submission without hand-typing each page.

Quick Start

Tell the AI: "Use the pdf skill to extract text from invoice-q3.pdf and return the extracted content."

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 scanned PDF using OCR?

To extract text and tables from a scanned PDF, OCR is applied to parse image-based content into searchable text. This process uses layout-aware extraction to capture structured table data, transforming static PDFs into searchable text and structured information.

What is the best way to automate PDF form filling for a batch of documents?

Automating PDF form filling involves detecting fillable fields, extracting field metadata, and validating bounding boxes to produce filled outputs. For non-fillable documents, text annotations are applied at specified coordinates to reliably complete the form filling process.

Can I merge, split, and add watermarks to PDFs programmatically?

Yes, you can merge, split, rotate pages, and add watermarks to PDFs programmatically. These document transformation capabilities allow you to edit and restructure PDF layouts while applying encryption or decryption for secure file handling.

Does PDF text extraction work with image-based documents?

PDF text extraction works with image-based documents by utilizing OCR technology. It processes scanned PDFs through image conversion and optical character recognition, ensuring text extraction succeeds even when the source PDF lacks embedded text layers.

How do I handle PDF form filling when the document has no fillable fields?

When a PDF has no fillable fields, form filling is handled by adding text annotations at specific coordinates. The system applies coordinate validation logic to accurately position text annotations on non-fillable PDFs, producing a completed output ready for submission.

What are the limitations of extracting structured data from PDF tables?

Extracting structured data from PDF tables relies on layout-aware parsing, which may face limitations with highly irregular or merged cell structures. Table extraction works best with clearly defined grid layouts to reliably return structured data for analysis.