doc-reader

Extracts text and structured data from PDFs, office files, and source code with OCR support.

Updated Jul 29, 2026
One-click install
npx skills add https://github.com/santoosaraujo/vibe-trading-claude --skill doc-reader-santoosaraujo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/santoosaraujo/vibe-trading-claude/tree/main/.claude/skills/doc-reader
Command: npx skills add https://github.com/santoosaraujo/vibe-trading-claude --skill doc-reader-santoosaraujo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rapidocr_onnxruntime.

What problem does it solve?

This skill eliminates the friction of handling diverse file formats by providing a single, unified interface to extract text and structured data from virtually any document type, including PDFs, spreadsheets, and images.

Core Features & Use Cases

  • Universal Parsing: Automatically detects and processes formats like PDF, Word, Excel, PowerPoint, and various source code files.
  • Integrated OCR: Uses local or cloud-based engines to extract text from scanned documents, images, and non-selectable PDFs.
  • Use Case: Quickly ingest a mix of annual reports, contract documents, and sales spreadsheets to perform cross-document analysis without needing to manually open each file in different applications.

Quick Start

Use the doc-reader skill to extract the full text and table data from the file located at uploads/annual_report.pdf.

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 and structured data from a PDF file?

To extract text and structured data from a PDF, you can use an automated document parsing interface that processes PDFs, office suites, and source code files into a standardized JSON format for downstream analysis.

Can I perform OCR on scanned images and non-selectable PDFs?

Yes, you can perform OCR on scanned images and non-textual PDFs by configuring local or cloud-based engines to extract text automatically during the document parsing process.

Does this document analysis tool support spreadsheets and Word documents?

Yes, this document analysis tool supports universal parsing across formats including Word, Excel, PowerPoint, PDFs, and source code files, automatically detecting the format to extract relevant data.

What is the best way to automate data extraction from mixed document formats?

The best way to automate data extraction from mixed document formats is using a unified interface that ingests diverse files like annual reports and spreadsheets, returning a standardized JSON envelope for cross-document analysis.

Do I need rapidocr_onnxruntime to extract text from scanned documents?

You need the rapidocr_onnxruntime dependency to enable integrated OCR capabilities for extracting text from scanned documents, images, and non-textual PDF pages without manual intervention.

What output format should I expect from automated document parsing?

Automated document parsing provides a standardized JSON envelope containing the extracted text and structured data, which you can then use directly for downstream content summarization and analysis tasks.