xlsx-reader

Extract cells, tables, formulas, and metadata from Excel workbooks.

4|10|Updated Feb 20, 2026
One-click install
npx skills add https://github.com/Stratio/genai-agents --skill xlsx-reader
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xlsx-reader
Source: https://github.com/Stratio/genai-agents/tree/main/shared-skills/xlsx-reader
Command: npx skills add https://github.com/Stratio/genai-agents --skill xlsx-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openpyxl, pandas, lxml, and includes scripts (resource) components.

What problem does it solve?

Read and extract meaningful content from Excel workbooks, including cells, tables, formulas, metadata, and sheet structure, with reliable diagnostics and flexible modes.

Core Features & Use Cases

  • Two-mode operation: quick mode for fast extraction and deep mode for step-by-step diagnosis when formulas or cross-sheet references matter.
  • Multi-engine resilience: auto-fallback between openpyxl, pandas, and low-level XML parsing to maximize success across .xlsx, .xlsm, and legacy .xls.
  • Structured outputs: produce Markdown, CSV, or JSON reports per sheet, with safe handling of large files and hidden sheets.

Quick Start

Provide a workbook path to extract its contents with the default Markdown output.

Frequently Asked Questions about xlsx-reader

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

FAQPage Schema
How do I extract data and formulas from an Excel workbook into a structured format?

Extract Excel workbook content including cells, tables, formulas, and metadata by reading single or multi-sheet files. Use deterministic extraction with openpyxl, pandas, and XML parsing to output structured Markdown, CSV, or JSON reports.

Does this approach support reading legacy .xls files as well as .xlsx and .xlsm formats?

Yes, reading legacy .xls files alongside .xlsx and .xlsm is supported through multi-engine resilience. The extraction process auto-falls back between openpyxl, pandas, and low-level XML parsing to maximize success across all three formats.

What is the difference between quick mode and deep mode when parsing Excel sheets?

Quick mode provides fast extraction of workbook content, while deep mode offers step-by-step diagnosis when formulas or cross-sheet references matter. Both modes handle sheet structure and metadata, producing structured outputs.

Can I extract images and charts from an Excel file using openpyxl and pandas?

Yes, extracting images and charts from Excel workbooks is possible using optional extraction features. The process reads workbook content with openpyxl and pandas, handling cells, tables, and metadata while safely processing hidden sheets.

What is the best way to handle large Excel files with hidden sheets and complex cross-sheet references?

Use deep mode for step-by-step diagnosis of complex cross-sheet references in large Excel files. The multi-engine approach auto-falls back to low-level XML parsing, ensuring safe handling of hidden sheets while producing structured outputs.

Why does Excel data extraction fail on certain workbooks, and how does multi-engine fallback help?

Excel data extraction fails when standard engines cannot parse complex workbook structures. Multi-engine resilience auto-falls back between openpyxl, pandas, and low-level XML parsing with diagnostic support to maximize extraction success across .xlsx, .xlsm, and .xls.