PDF Extractor Agent

Extracts dialogue from educational PDFs into structured JSON using OCR and pattern detection.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/mdrashedmamun/fluentstep-ielts-roleplay-engine --skill pdf-extractor-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: PDF Extractor Agent
Source: https://github.com/mdrashedmamun/fluentstep-ielts-roleplay-engine/tree/main/.claude/agents/pdf-extractor
Command: npx skills add https://github.com/mdrashedmamun/fluentstep-ielts-roleplay-engine --skill pdf-extractor-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of structured dialogue content from various educational PDF formats, converting them into a universal JSON format for further processing.

Core Features & Use Cases

  • Universal Dialogue Detection: Extracts dialogue from Oxford, Cambridge, and custom textbook formats.
  • Multi-Strategy Text Extraction: Employs pdftotext, pdf-parse, and OCR fallbacks for robust text retrieval.
  • Pattern Recognition: Identifies speaker patterns and scores dialogue richness for IELTS training suitability.
  • Use Case: Convert a PDF textbook chapter into a structured JSON file containing all dialogues, ready for an AI to use in a roleplay scenario.

Quick Start

Use the PDF Extractor Agent to extract dialogue from the file 'ielts-practice-dialogue.pdf'.

Frequently Asked Questions about PDF Extractor Agent

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

FAQPage Schema
How do I extract dialogue from a PDF textbook for AI roleplay scenarios?

To extract dialogue from a PDF textbook, this Skill uses a multi-stage strategy involving pdftotext, pdf-parse, and Tesseract OCR. It identifies speaker patterns and outputs a universal dialogue JSON format, structured by educational units, ready for AI roleplay scenarios.

Can I extract structured text from Cambridge IELTS and Oxford New Headway PDFs?

Yes, you can extract structured text from Cambridge IELTS and Oxford New Headway PDFs. The Skill features universal dialogue detection tailored for these specific educational formats, scoring dialogue richness specifically to determine IELTS training suitability.

What is the best way to convert educational PDF content into chunked JSON files?

The best way to convert educational PDF content into chunked JSON files is using a multi-strategy extraction pipeline. This Skill employs pattern detection and confidence scoring to identify dialogues, chunking the universal JSON output by educational units automatically.

Does this PDF text extraction tool use OCR fallbacks for scanned educational documents?

Yes, this PDF text extraction tool uses Tesseract OCR as a fallback. It employs a robust multi-stage text retrieval strategy combining pdftotext and pdf-parse to ensure accurate dialogue extraction from diverse and potentially scanned educational sources.

How are speaker patterns detected when extracting dialogue from custom textbook layouts?

Speaker patterns are detected using advanced pattern recognition and confidence scoring during the text extraction process. This mechanism identifies dialogue structures within custom textbook layouts and standard formats, converting them into a structured universal dialogue JSON output.