document-processing

Name: document-processing
Availability: InStock
Author: smukerji

Convert documents between PDF, DOCX, XLSX, and other formats.

1|Updated Mar 15, 2026

Search Tags:#pdf #generation #xlsx #conversion #docx #processing #document

Ready to run

npx skills add https://github.com/smukerji/openTorriAI --skill document-processing-smukerji

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-processing
Source: https://github.com/smukerji/openTorriAI/tree/main/apps/api/skills/bundled/document-processing
Command: npx skills add https://github.com/smukerji/openTorriAI --skill document-processing-smukerji

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, reportlab, python-docx, openpyxl, pandas, python-pptx, beautifulsoup4, jinja2, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the handling of various document formats, automating the creation, conversion, parsing, and transformation of files like PDFs, DOCX, XLSX, and more.

Core Features & Use Cases

Multi-format Support: Reads and writes a wide array of document types including PDF, DOCX, XLSX, PPTX, CSV, Markdown, and HTML.
Content Transformation: Accurately converts between formats while preserving structure, formatting, and Unicode characters.
Document Generation: Creates new documents from scratch with specified layouts, styles, and content.
Use Case: Convert a complex PDF report into an editable DOCX file, ensuring all tables and text are accurately represented.

Quick Start

Use the document-processing skill to convert the attached file 'report.pdf' into a markdown document.

Frequently Asked Questions about document-processing

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

FAQPage Schema

How do I convert a PDF to DOCX while preserving tables and formatting?▼

Converting a PDF to DOCX while preserving tables and formatting requires a tool that accurately extracts content and reconstructs the document structure. This process ensures text and tables are correctly represented in the editable DOCX file.

Can I generate a new PDF or XLSX file from scratch with specific layouts?▼

Yes, generating new PDF or XLSX files from scratch with specific layouts is fully supported. This is achieved using libraries like reportlab and openpyxl to programmatically construct documents with your specified styles and content.

What is the best way to extract content from HTML and convert it to Markdown?▼

The best way to extract content from HTML and convert it to Markdown is by using parsing libraries like beautifulsoup4 to read the HTML structure. This approach accurately transforms the content while maintaining the intended formatting and layout.

Does this approach support reading and writing PPTX presentations?▼

Yes, this approach fully supports reading and writing PPTX presentations using the python-pptx library. It enables you to parse existing presentation structures and generate new slides with programmatically specified layouts and content.

What libraries are needed for multi-format document conversion?▼

For multi-format document conversion across PDF, DOCX, and XLSX, you need libraries such as PyMuPDF, python-docx, openpyxl, and pandas. These dependencies handle content extraction, formatting preservation, and structural transformation accurately.

Why does my document conversion lose Unicode characters?▼

Document conversion might lose Unicode characters if the processing tool lacks explicit encoding preservation support. Using a robust document processing approach ensures accurate conversion while preserving Unicode characters and original structure.