doc-reader

Name: doc-reader
Availability: InStock
Author: ggwujun

Extract text from PDFs, Word, Excel, images, and code files.

Updated Jun 12, 2026

Search Tags:#ocr #pdf #document #data-processing #text-extraction #format-dispatch

Ready to run

npx skills add https://github.com/GGwujun/SigmX --skill doc-reader-ggwujun

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/GGwujun/SigmX/tree/main/agent/src/skills/doc-reader
Command: npx skills add https://github.com/GGwujun/SigmX --skill doc-reader-ggwujun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Read and extract text from a wide range of document formats including PDFs, Word, Excel, PowerPoint, images (OCR), CSV/JSON/YAML, HTML/XML, and source code, returning a unified text envelope for downstream processing.

Core Features & Use Cases

Automatic format dispatch by extension using a single read_document tool for consistent results.
OCR fallback for image or scanned documents to ensure text retrieval.
Use cases include archiving, data extraction, compliance reviews, and content analysis across legal, finance, and research contexts.

Quick Start

Upload a supported document to your workflow and call read_document on the file path to retrieve a unified text envelope.

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 Word document automatically?▼

Extracting text from a PDF or Word document is done by calling a single read_document tool that automatically dispatches by file extension and returns a unified text envelope for consistent downstream processing.

Does OCR work on scanned PDFs and images for text extraction?▼

OCR works on scanned PDFs and images by applying an automatic fallback mechanism. The tool triggers OCR when needed, extracting readable text from image-based documents for your data analysis and archiving.

What is the best way to parse multiple file formats like Excel, CSV, and HTML?▼

The best way to parse multiple formats like Excel, CSV, and HTML is to use a universal document reader that handles format dispatch by extension, yielding a structured envelope containing status, format, and text.

Can I extract text from source code and YAML files for compliance reviews?▼

You can extract text from source code and YAML files for compliance reviews. The reader supports these formats alongside XML and JSON, returning consistent text output for auditing and content analysis.

Do I need any external dependencies to read PowerPoint and Excel files?▼

No external dependencies are required to read PowerPoint and Excel files. The tool operates standalone, automatically dispatching by file extension to retrieve text without needing additional environment setup.

Why does my text extraction return a structured envelope instead of plain text?▼

Text extraction returns a structured envelope to provide consistent results across all formats. This envelope includes the extraction status, detected format, and the text, satisfying operational requirements for downstream data processing.