pdf

Extract text and fill forms in PDF documents.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/loanntc/Paave --skill pdf-loanntc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/loanntc/Paave/tree/main/skills/pdf
Command: npx skills add https://github.com/loanntc/Paave --skill pdf-loanntc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

You spend too much time manually handling PDF documents—extracting information, filling forms, and ensuring outputs are correct—especially when forms are complex or PDFs aren’t consistently structured.

Core Features & Use Cases

  • PDF text and layout extraction: Extract readable text and work with structured elements (like tables) from PDFs for downstream use.
  • PDF form handling (fillable + non-fillable): Fill actual AcroForm fields when available, or add text annotations using generated field coordinates when forms are not fillable.
  • Operational PDF transformations: Combine, split, rotate, and create/modify PDFs, plus OCR for scanned documents (when needed).

Quick Start

Ask: "Fill the PDF form in my file using the provided coordinates, validate the bounding boxes, and return a completed output PDF."

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 for data processing?

To extract text and tables from PDF documents, this Skill uses pdfplumber to parse readable text and structured layout elements like tables. This enables downstream data processing workflows by converting unstructured PDF content into structured formats.

Can I fill non-fillable PDF forms using coordinate transforms and bounding boxes?

Yes, you can fill non-fillable PDF forms by generating field coordinates and adding text annotations with bounding-box checks. For fillable forms, it directly populates AcroForm fields using scriptable field discovery and validation.

Does OCR work with scanned PDFs to make them searchable?

Yes, OCR works with scanned PDFs to make them searchable by leveraging pytesseract and pdf2image. This converts scanned document images into machine-readable text, allowing you to data extraction from non-digital PDFs.

What is the best way to split, merge, and rotate PDF files in an automated workflow?

The best way to split, merge, and rotate PDF files in an automated workflow is using pypdf for operational transformations. It reliably combines, splits, and modifies documents to produce correctly ordered outputs.

Do I need Python libraries like pdfplumber and pypdf installed to automate PDF form filling?

Yes, you need Python libraries like pdfplumber and pypdf installed to automate PDF form filling. These dependencies handle field discovery, validation, and document transformations required for deterministic outputs.