doc-reader

Extract text and structured data from PDFs, Office documents, images, and source code.

Updated Jul 8, 2026
One-click install
npx skills add https://github.com/hxhyyy/Vibe-Trading --skill doc-reader-hxhyyy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/hxhyyy/Vibe-Trading/tree/main/agent/src/skills/doc-reader
Command: npx skills add https://github.com/hxhyyy/Vibe-Trading --skill doc-reader-hxhyyy

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.

Core Features & Use Cases

  • Universal Parsing: Automatically detects and processes PDFs, Office documents, images via OCR, and source code files.
  • Structured Output: Returns data in a consistent JSON envelope, making it easy to integrate into downstream analysis workflows.
  • Use Case: Quickly ingest a mix of project requirements in Word, financial data in Excel, and technical specifications in PDF to generate a comprehensive project summary.

Quick Start

Use the doc reader to extract all text and content 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 from a PDF and Office documents automatically?

You can extract text from PDFs and Office documents automatically by using a unified parsing interface that detects file extensions and returns structured JSON data for downstream analysis.

Can I use OCR to extract structured data from images?

Yes, you can use OCR to extract structured data from images by utilizing built-in OCR capabilities that ensure high-fidelity content retrieval and return the output in a consistent JSON envelope.

Does rapidocr-onnxruntime support extracting tables from source code files?

While rapidocr-onnxruntime provides OCR capabilities for images, the document parser uses specialized logic to extract text and structured data from source code files, supporting diverse document analysis tasks.

What is the best way to ingest mixed file formats like Excel and Word for project summaries?

The best way to ingest mixed file formats like Excel and Word is using a universal parsing tool that automatically detects formats and outputs consistent data to generate comprehensive project summaries.

What are the limitations of document parsing for contract review?

Limitations of document parsing for contract review depend on the specialized parsing logic and OCR capabilities, which ensure high-fidelity retrieval but may require consistent JSON output formatting for automated report summarization.