Clean Data Xls

This handles the grunt work of cleaning messy spreadsheets before analysis. It profiles your columns, detects whitespace issues, inconsistent casing, numbers stored as text, mixed date formats, duplicates, and type mismatches, then shows you a summary table of proposed fixes before touching anything. The smart bit is that it writes formulas like TRIM() and VALUE() in helper columns instead of just overwriting your data, so you can see and audit the transformations. It walks through each category of fix and asks for confirmation on destructive operations. Works in Excel via Office JS or on standalone .xlsx files with Python. Good for when you inherit a dataset and need to normalize it without guessing what silent changes got made.

skills.sh installs: 2.1K
GitHub stars: 41.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/financial-services --skill clean-data-xls --agent claude-code

Installs into .claude/skills of the current project.

Files

Clean Data

Clean messy data in the active sheet or a specified range.

Environment

If running inside Excel (Office Add-in / Office JS): Use Office JS directly (Excel.run(async (context) => {...})). Read via range.values, write helper-column formulas via range.formulas = [["=TRIM(A2)"]]. The in-place vs helper-column decision still applies.
If operating on a standalone .xlsx file: Use Python/openpyxl.

Workflow

Step 1: Scope

If a range is given (e.g. A1:F200), use it
Otherwise use the full used range of the active sheet
Profile each column: detect its dominant type (text / number / date) and identify outliers