skills.rest
AbeJitsu
AbeJitsuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

pdf-page-extract

Extract text spans with font metadata, PNG images, and page mappings from PDFs.

Updated Nov 13, 2025
Search Tags:#pdfplumber#pdf extraction#image extraction#pymupdf#text mining#data preparation#document parsing
One-click install
npx skills add https://github.com/AbeJitsu/Game-Settings-Panel --skill pdf-page-extract
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-page-extract
Source: https://github.com/AbeJitsu/Game-Settings-Panel/tree/main/.claude/skills/calypso/pdf-page-extract
Command: npx skills add https://github.com/AbeJitsu/Game-Settings-Panel --skill pdf-page-extract

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Getting structured, high-fidelity data from PDFs is foundational for AI processing but often complex and time-consuming. This Skill deterministically extracts all necessary data from PDF pages, creating a robust, AI-ready foundation for downstream tasks.

Core Features & Use Cases

  • Rich Text Extraction: Pulls text spans with font metadata (size, style, position) using PyMuPDF and pdfplumber for detailed content analysis.
  • High-Resolution Rendering: Converts PDF pages to 300+ DPI PNG images, providing a precise visual reference for AI.
  • Page Mapping: Establishes an authoritative mapping of PDF indices to book page numbers for consistent referencing and navigation.
  • Use Case: Prepare a PDF textbook chapter by extracting all text, images, and visual layouts, creating a complete set of artifacts for AI-driven HTML conversion.

Quick Start

Extract rich data from pages 15 to 28 of the attached 'PREP-AL 4th Ed 9-26-25.pdf'.

Frequently Asked Questions about pdf-page-extract

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

FAQPage Schema
How do I extract text with font metadata from a PDF for AI processing?▼

PDF page extraction pulls text spans with font size, style, and position data using PyMuPDF and pdfplumber, enabling detailed content analysis and deterministic downstream AI workflows without manual reformatting.

Can I convert PDF pages to high-resolution images for document analysis?▼

Yes, this Skill renders PDF pages to 300+ DPI PNG images, providing precise visual references that preserve layout and formatting for AI-driven processing and HTML conversion tasks.

How do I establish consistent page mapping between PDF indices and book pages?▼

Page mapping creates an authoritative correspondence between PDF file indices and physical book page numbers, enabling deterministic referencing and navigation across multi-page scholarly documents and textbook chapters.

What's the best way to prepare multi-page textbooks for AI-ready content extraction?▼

Extract rich PDF data—text with font metadata, rendered images, and page mappings—in a single workflow, creating structured artifacts across all pages and chapters without requiring separate tools or manual data alignment.

Can I extract images embedded in PDFs alongside text content?▼

Yes, this Skill extracts both rendered PNG images and text spans from PDF pages simultaneously, with artifact persistence and data integrity checks to ensure complete, high-fidelity content recovery.

Do I need multiple tools to handle text, images, and page mapping from PDFs?▼

No, PDF page extraction consolidates text mining, image extraction, and page mapping into one deterministic process with input validation and output persistence, eliminating tool fragmentation for document preparation workflows.

Related Skills

Explore More Data & Analytics Skills→
tkhongsaptkhongsap
1

pdf

Extract text and tables from PDF documents using Python libraries.

Community
Advanced
smallnestsmallnest
190

markitdown

Convert PDFs, Word, Excel, HTML, and images with OCR into Markdown.

Community
Advanced
notaustindanielsnotaustindaniels

pdf

Extract text and tables from PDFs using Python libraries.

Community
Advanced
guccangguccang
3

ocr-and-documents

Extract text, tables, metadata, and images from PDFs and scanned documents.

Community
Advanced