pdf

Name: pdf
Availability: InStock
Author: estrella-231

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

Updated May 24, 2026

Search Tags:#ocr #pdf #form filling #text extraction #table extraction #document transformation

Ready to run

npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill pdf-estrella-231

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/pdf
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill pdf-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, PIL, reportlab, qpdf, poppler-utils, pytesseract, and includes scripts (resource) and references (resource) components.

What problem does it solve?

You waste time manually reading PDFs, extracting tables, or filling form fields that should be handled automatically.

Core Features & Use Cases

PDF text and table extraction: Extract page text and structured tables for analysis, reporting, or downstream processing.
PDF transformations: Merge, split, rotate pages, extract images, apply watermarks, and generate new PDFs when needed.
Form handling: Detect fillable fields and fill them, or add precise text annotations for non-fillable PDFs.

Quick Start

Ask the AI to fill your PDF form by providing your PDF file and a fields.json that contains the target field values and page/coordinate mappings.

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 using OCR, you need a searchable OCR conversion process. This involves rasterizing PDF pages into images and applying optical character recognition to transform them into usable digital text and structured table data.

How do I programmatically fill PDF form fields and annotate non-fillable PDFs?▼

To programmatically fill PDF form fields, you map target field values to detected fillable areas using a JSON configuration. For non-fillable PDFs, you apply precise coordinate handling to add text annotations directly onto the document pages.

What is the best way to merge, split, and rotate PDF pages programmatically?▼

The best way to merge, split, and rotate PDF pages programmatically is through document transformation operations. These functions modify PDF structures directly, allowing you to reorganize, extract, or alter page orientations without manual editing.

Does Python support generating new PDFs and applying watermarks to existing documents?▼

Yes, Python supports generating new PDFs and applying watermarks to existing documents. By utilizing dedicated PDF generation and transformation libraries, you can create documents from scratch or overlay watermark images and text onto existing pages.

What are the limitations of extracting structured tables from complex PDF documents?▼

Extracting structured tables from complex PDF documents faces limitations regarding coordinate handling and layout detection. Tables merged across multiple pages, lack clear bounding boxes, or feature nested structures often require manual boundary correction to achieve accurate extraction.