doc-reader

Extract text from multiple document formats into a unified JSON envelope.

1|Updated Jun 23, 2026
One-click install
npx skills add https://github.com/644408071-design/Kokpop --skill doc-reader-644408071-design
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-reader
Source: https://github.com/644408071-design/Kokpop/tree/main/agent/src/skills/doc-reader
Command: npx skills add https://github.com/644408071-design/Kokpop --skill doc-reader-644408071-design

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdfminer.six, PyMuPDF, Pillow, unidecode, tabula-py, camelot-py, python-docx, openpyxl, pptx, lxml, html5lib, html2text, python-docx, openpyxl, camelot-py, tabula-py, PyMuPDF, Pillow, unidecode, python-docx, openpyxl, camelot-py, tabula-py, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the issue of converting various document formats to editable text, eliminating the need for manual data entry.

Core Features & Use Cases

  • Multi-format Support: Read common document formats such as PDF, Word, Excel, PowerPoint, images, CSV, plain text, JSON, YAML, TOML, HTML/XML, and source code files.
  • Universal Tool Usage: Use the read_document tool to extract text from any supported file format.
  • Use Case: With this Skill, you can quickly extract text from a contract or summary important information from a research paper.

Quick Start

Use the doc-reader skill to read the text from the attached PDF file 'contract.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 convert it to an editable format?

You can extract text from multiple document formats including PDF, Word, Excel, PowerPoint, images, CSV, HTML/XML, and various source code files. This multi-format support consolidates unstructured documents into a unified JSON envelope for analysis.

What's the best way to extract text from multiple document formats into one consistent structure?

Using a unified document parsing tool is the best way to extract text from formats like PDF, Word, and Excel into a single JSON envelope. It eliminates manual data entry by standardizing diverse unstructured files into machine-readable text.

Can I use Python libraries to automate document conversion for scanned images and presentations?

Yes, you can automate document conversion for scanned images and presentations using Python libraries. This Skill requires specific parsing and OCR dependencies like PyMuPDF, Pillow, and python-pptx to extract text from these file types.

Does extracting tables from PDF documents require separate dependencies?

Yes, extracting tables from PDF documents requires specific dependencies for tabular data parsing. This Skill utilizes libraries like tabula-py and camelot-py alongside PyMuPDF to accurately capture and convert tabular structures into editable text.

Why do I need OCR for document processing when working with image files?

You need OCR for document processing with image files because standard text parsers cannot read text embedded in pixels. OCR mechanisms convert visual text data into machine-readable strings, enabling unstructured image content to become editable text.