spreadsheets

Process and clean non-tabular spreadsheet files with header detection and type coercion.

25|3|Updated Jul 14, 2026
One-click install
npx skills add https://github.com/nimadorostkar/Claude-Skills-collection --skill spreadsheets-nimadorostkar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spreadsheets
Source: https://github.com/nimadorostkar/Claude-Skills-collection/tree/main/skills/documents/spreadsheets
Command: npx skills add https://github.com/nimadorostkar/Claude-Skills-collection --skill spreadsheets-nimadorostkar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, openpyxl.

What problem does it solve?

This skill solves the common frustration of working with real-world, non-tabular spreadsheets that contain merged cells, title rows, and inconsistent formatting that break standard data analysis tools.

Core Features & Use Cases

  • Robust Parsing: Automatically detects actual header rows and handles messy layouts like merged cells or multi-table sheets.
  • Data Sanitization: Cleans whitespace, coerces data types, and identifies total rows that often cause calculation errors.
  • Professional Formatting: Generates clean, human-readable workbooks with frozen panes, auto-filters, and conditional formatting.

Quick Start

Use the spreadsheets skill to clean the attached sales-data.xlsx file and extract the revenue totals into a structured format.

Frequently Asked Questions about spreadsheets

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

FAQPage Schema
How do I clean messy Excel files with merged cells and title rows?

To clean messy Excel files with merged cells and title rows, the spreadsheets skill automatically detects actual header rows, sanitizes whitespace, and coerces data types. It processes non-tabular xlsx files to ensure accurate data analysis and reporting.

Why do my spreadsheet totals show doubled rows after data cleaning?

Doubled rows after data cleaning often occur when total rows are not properly identified. The spreadsheets skill prevents this by validating input structures and detecting total rows that commonly cause calculation errors during type coercion.

What's the best way to parse a multi-table sheet in pandas without silent join failures?

The best way to parse multi-table sheets in pandas without silent join failures is using the spreadsheets skill, which robustly parses complex layouts and requires validation of input structures to prevent silent join failures.

Does openpyxl support generating professional workbooks with auto-filters and conditional formatting?

Yes, openpyxl supports generating professional workbooks. The spreadsheets skill leverages it alongside pandas to produce clean, human-readable workbooks featuring frozen panes, auto-filters, and conditional formatting.

Can I automate data cleaning for CSV and xlsx files with inconsistent formatting?

Yes, you can automate data cleaning for CSV and xlsx files with inconsistent formatting. The spreadsheets skill sanitizes whitespace, coerces data types, and handles non-tabular layouts to ensure accurate data analysis.