pdf

Extract text, tables, and media from PDF files using pypdf and pdfplumber.

Updated May 26, 2026
One-click install
npx skills add https://github.com/XWIlluDelu/agent-share --skill pdf-xwilludelu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/XWIlluDelu/agent-share/tree/main/lib/pdf
Command: npx skills add https://github.com/XWIlluDelu/agent-share --skill pdf-xwilludelu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, PIL, pytesseract, pypdfium2, reportlab, pandas, ImageMagick(poppler), qpdf(poppler), and includes references (resource) components.

What problem does it solve?

PDFs are difficult to work with using copy-and-paste alone, especially when you need reliable text extraction, form filling, or page-level transformations.

Core Features & Use Cases

  • Text extraction & table parsing: Extract readable text and tables from PDFs (including extracting layout-oriented text).
  • PDF transformations: Merge, split, rotate pages, add watermarks, encrypt/decrypt, and extract embedded images.
  • PDF form handling: Detect fillable fields, fill them programmatically, and add annotations to non-fillable forms using coordinate-based placement.

Quick Start

Ask the pdf skill to fill a PDF form by using a provided fields.json and produce a filled 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 a scanned PDF using OCR?

To extract text and tables from a scanned PDF, the process renders pages using pdf2image and applies pytesseract OCR. It maps page content into actionable coordinates to reliably digitize documents, extracting layout-oriented text that standard copy-and-paste misses.

How do I programmatically fill a PDF form using a JSON file?

To programmatically fill a PDF form, you provide a fields.json file mapping values to fillable fields. The skill detects available form fields and outputs a completed PDF, or uses coordinate-based placement to add annotations to non-fillable forms.

Can I merge, split, or add watermarks to PDF pages in bulk?

Yes, you can merge, split, rotate pages, and add watermarks to PDF files. It supports batch processing for document digitization and operational use, handling page-level transformations reliably using libraries like pypdf and qpdf.

Does this approach work with both native digital PDFs and scanned documents?

Yes, it processes both native and scanned PDFs. For native documents, pdfplumber extracts text and tables directly. For scanned inputs, it renders pages and applies pytesseract OCR to map content into actionable text and coordinates.

What is the best way to extract embedded images from PDF files?

The best way to extract embedded images from PDFs is using the built-in page transformation features. It leverages libraries like PIL and pypdfium2 to isolate and export embedded media, integrating image extraction into broader document digitization workflows.

Why does text extraction fail on some PDFs without OCR?

Text extraction fails on scanned PDFs because they contain images rather than embedded text. Standard parsing with pdfplumber returns nothing, requiring the skill to render pages with pdf2image and apply pytesseract OCR to recognize the text.