Clean Data

Clean up messy spreadsheet data — trim whitespace, fix inconsistent casing, convert numbers-stored-as-text, standardize dates, remove duplicates, and flag mixed-type columns. Use when data is messy, inconsistent, or needs prep before analysis. Triggers on "clean this data", "clean up this sheet", "normalize this data",

Overview

The Clean Data skill, part of the fivetaku/claude-office-skills repository, provides automated data normalization for spreadsheet users interacting with Claude or Claude Code. This utility addresses common data integrity issues by trimming extraneous whitespace, correcting inconsistent text casing, and converting numerical values stored as strings back into numeric formats. It further assists in data preparation by standardizing date formats, identifying duplicate entries, and flagging columns containing mixed data types. By streamlining these repetitive tasks, the skill ensures datasets are properly formatted for subsequent analysis or reporting. This implementation is part of a collection of office-oriented tools that has gained traction on GitHub, currently maintaining over 50 stars for its utility in spreadsheet management.

Use Cases

Normalizing raw CSV exports by removing duplicate rows and trimming leading or trailing spaces.
Standardizing date formats and text casing across large datasets to ensure consistency for reporting.
Converting numbers-stored-as-text and identifying mixed-type columns before performing mathematical analysis.

Install Notes

# Review source first
open https://github.com/fivetaku/claude-office-skills/blob/main/claude-in-excel/clean-data-xls/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

Security Notes

Users should ensure they have the necessary permissions to process the contents of their spreadsheets through AI agents. As this skill operates on data provided within the chat or file context, sensitive information should be handled according to organizational data privacy policies.

Related Skills

Requirements for Outputs

anthropics/skills

Spreadsheets

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or fr

CodexClaude
pythontesting
150,001 starsSource linked

3-Statement Financial Model Template Completion

fivetaku/claude-office-skills

Spreadsheets

Complete, populate and fill out 3-statement financial model templates (Income Statement, Balance Sheet, Cash Flow Statement). Use when asked to fill out model templates, complete existing model frameworks, populate financial models with data, complete a partially filled IS/BS/CF framework, or link integrated financial

Claude CodeClaude
spreadsheetsaudit
56 starsSource linked

Audit Spreadsheet

fivetaku/claude-office-skills

Spreadsheets

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model, including financial-model integrity checks like BS balance, cash tie-out, and logic sanity. Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreads

Claude CodeClaude
spreadsheetsaudit
56 starsSource linked

DCF Model Builder

fivetaku/claude-office-skills

Spreadsheets

Real DCF (Discounted Cash Flow) model creation for equity valuation. Retrieves financial data from SEC filings and analyst reports, builds comprehensive cash flow projections with proper WACC calculations, performs sensitivity analysis, and outputs professional Excel models with executive summaries. Use when users need

Claude CodeClaude
spreadsheetsdocumentation
56 starsSource linked