doc-reader

Extract text from PDFs with OCR and structured JSON output.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/ebrahim-sani/trading-automation --skill doc-reader-ebrahim-sani
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/ebrahim-sani/trading-automation/tree/main/vibe-trading/agent/src/skills/doc-reader
Command: npx skills add https://github.com/ebrahim-sani/trading-automation --skill doc-reader-ebrahim-sani

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually extracting text from PDFs and performing OCR on scanned pages is time‑consuming and error‑prone. This Skill automates both processes, delivering ready‑to‑use text instantly.

Core Features & Use Cases

  • Automatic Text Extraction: Retrieves native text from digital PDFs within milliseconds.
  • OCR for Scanned Pages: Recognizes Chinese and English characters on image‑based pages, marking them with [OCR] in the output.
  • Page Range Selection: Allows reading specific pages or ranges to handle large documents efficiently.
  • Use Cases: Summarizing academic papers, analyzing annual reports, reviewing research documents, or extracting contract clauses.

Quick Start

Ask the doc-reader skill to read "paper.pdf" and return its full text.

Frequently Asked Questions about doc-reader

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

FAQPage Schema
How do I extract text from a scanned PDF document?

To extract text from a scanned PDF, OCR technology recognizes Chinese and English characters on image-based pages, marking them with [OCR] in the output. This converts scanned content into searchable text automatically.

Can I extract text from specific page ranges in a large PDF?

Yes, you can extract text from specific page ranges in a PDF. Page range selection allows you to read targeted pages, enabling efficient handling of large documents like annual reports or academic papers.

What is the best way to automate PDF text extraction for research papers?

Automating PDF text extraction retrieves native text from digital documents within milliseconds. It processes academic papers and research reports instantly, returning structured JSON with pagination and character counts.

Does PDF OCR support both Chinese and English characters?

Yes, PDF OCR supports both Chinese and English characters. It recognizes text on image-based scanned pages, ensuring accurate extraction for bilingual documents and converting them into searchable content.

How do I get structured JSON output from a PDF text extraction process?

Getting structured JSON output from PDF text extraction provides pagination and character counts alongside the retrieved content. It processes both native digital text and OCR results from scanned pages into a structured format.

Why does PDF text extraction return [OCR] tags in the output?

PDF text extraction returns [OCR] tags to identify pages processed through optical character recognition. This marks content recognized from image-based scanned pages, distinguishing it from native digital text retrieval.