skills.rest
executiveusa
executiveusaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

clean-data-xls

Clean spreadsheet ranges by repairing formatting, encodings, and mixed data types.

1|Updated May 16, 2026
Search Tags:#deduplication#data normalization#date standardization#spreadsheet cleaning#excel data prep#number-as-text
One-click install
npx skills add https://github.com/executiveusa/Cheggie-trade-V2 --skill clean-data-xls-executiveusa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: clean-data-xls
Source: https://github.com/executiveusa/Cheggie-trade-V2/tree/main/core/financial-skills/plugins/vertical-plugins/financial-analysis/skills/clean-data-xls
Command: npx skills add https://github.com/executiveusa/Cheggie-trade-V2 --skill clean-data-xls-executiveusa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It fixes messy spreadsheet data that breaks analysis by standardizing formatting, converting inconsistent values, and removing duplicate rows.

Core Features & Use Cases

  • Whitespace, Casing, and Encoding Repair: Trims whitespace, normalizes categorical casing, and addresses mojibake/non-printing characters.
  • Type Normalization (Text/Number/Date): Converts numeric values stored as text (including stray symbols) and standardizes mixed date formats within a column.
  • Data Quality Improvements: Detects blanks, flags mixed-type columns, and removes exact/near duplicates with confirmation safeguards.

Use case: When you receive a vendor export where prices are stored as text with currency symbols, dates use multiple formats, and category names vary in casing, this skill prepares the sheet for reliable financial analysis.

Quick Start

Tell the AI to clean this sheet using the clean-data-xls workflow.

Frequently Asked Questions about clean-data-xls

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

FAQPage Schema
How do I clean messy Excel data before analysis?▼

To clean messy Excel data, the skill profiles each column to standardize mixed date formats, repair inconsistent casing, and fix numeric values stored as text. It generates a before-change summary and uses helper-column formulas to prepare your spreadsheet for reliable downstream analysis.

What is the best way to convert numbers stored as text in a spreadsheet?▼

Converting numbers stored as text is handled through type normalization, which detects mixed data types and stray symbols like currency marks. The skill profiles the column, proposes changes, and applies helper-column formulas to safely convert text values into analysis-ready numeric formats.

How do I repair corrupted text encoding and mojibake in xlsx files?▼

Repairing corrupted text encoding and mojibake in xlsx files involves detecting non-printing characters and applying whitespace and encoding repair. The skill normalizes categorical casing and addresses these inconsistencies while showing a before-change summary for confirmation.

Can I remove duplicate rows from an active Excel sheet without losing original data?▼

You can remove exact and near duplicates from an active Excel sheet while preserving original data. The skill prefers helper-column formulas over hardcoded overwrites and includes confirmation safeguards to prevent destructive edits during the deduplication process.

Does this spreadsheet cleaning workflow work with standalone .xlsx files?▼

Yes, the spreadsheet cleaning workflow works with standalone .xlsx files. It applies the same data profiling, type normalization, and encoding repair to standalone files as it does to active-sheet ranges in Excel.

Why does data normalization require confirming destructive edits?▼

Data normalization requires confirming destructive edits to prevent accidental data loss. The skill proposes a before-change summary and prefers helper-column formulas over hardcoded overwrites, ensuring you review mixed-type column flags and blank detections before any modifications are applied.

Related Skills

Explore More Data & Analytics Skills→
anthropicsanthropics
34.1k

clean-data-xls

Clean and standardize messy spreadsheet data in Excel or .xlsx files using Python/openpyxl.

Official
Intermediate
logeshv586-codelogeshv586-code

xlsx

Analyze spreadsheet data and create charts with openpyxl, pandas, and matplotlib.

Community
Advanced
nvmohinaninvmohinani

clean-data-xls

Cleans and standardizes messy Excel spreadsheet data across ranges and .xlsx files using Excel/Office JS or Python/openpyxl workflows.

Community
Intermediate
cwstedctwcwstedctw

clean-data-xls

Normalize whitespace, casing, numeric and date formats in spreadsheet data.

Community
Intermediate