csv-clean

Detect and fix CSV data quality issues including subtotal rows, formatted numbers, and mixed date formats.

Updated Jul 7, 2026
One-click install
npx skills add https://github.com/hivgb1-ai/do-better-workspace-v2 --skill csv-clean-hivgb1-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: csv-clean
Source: https://github.com/hivgb1-ai/do-better-workspace-v2/tree/main/.claude/skills/csv-clean
Command: npx skills add https://github.com/hivgb1-ai/do-better-workspace-v2 --skill csv-clean-hivgb1-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? CSV exports from banks, Excel, and APIs often contain subtotal rows, comma-formatted numbers, inconsistent date formats, and crosstab layouts that break downstream analysis. This Skill analyzes and cleans these issues automatically with pandas. ## Core Features & Use Cases - Quality Analysis: Run an info-only scan that detects subtotal rows, text-formatted numbers, mixed date formats, and crosstab structures, then suggests the right fix options. - Automated Cleaning: Remove subtotal/total rows, strip currency symbols and commas from numbers, normalize dates to YYYY-MM-DD (including Korean date formats), and unpivot crosstab tables into tidy data. - Use Case: You exported a bank statement CSV where amounts look like "1,234,500" and dates mix "2024.01.15" with "2024년 1월 20일". Run the cleaner to normalize everything into analysis-ready rows. ## Quick Start Ask the AI to clean the attached CSV file by removing subtotal rows and normalizing the numbers and dates.

Frequently Asked Questions about csv-clean

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

FAQPage Schema
How do I remove subtotal and total rows from a CSV file?

Run the script with the --remove-subtotals flag to detect and drop rows containing keywords like subtotal, total, 소계, or 합계. Use --info first to preview which rows will be removed before applying changes.

How to convert comma-formatted numbers in CSV to numeric values?

Use the --clean-numbers flag to auto-detect columns with commas, currency symbols, or percent signs and convert them to numeric values. To target specific columns only, pass them with --clean-numbers-cols.

Can I normalize mixed date formats in a CSV column?

Yes, the --normalize-dates flag parses formats like YYYY-MM-DD, YYYY.MM.DD, YYYYMMDD, and Korean YYYY년 M월 D일, then rewrites them to a uniform format. Set the target with --date-format, defaulting to %Y-%m-%d.

Does the CSV cleaner overwrite my original file?

By default it writes a new file named with a _cleaned suffix, leaving the original untouched. Use --inplace to overwrite the original or --output to specify a custom path.

What Python dependencies does the CSV cleaning script need?

The script requires pandas version 2.0.0 or higher, installed via pip install pandas or the included requirements.txt. All other functionality uses Python standard library modules.