Data Cleaner

Analyze, clean, and validate tabular datasets with quality reports.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/brook-miller/claude-skill-data-cleaner --skill data-cleaner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Data Cleaner
Source: https://github.com/brook-miller/claude-skill-data-cleaner/tree/main/.
Command: npx skills add https://github.com/brook-miller/claude-skill-data-cleaner --skill data-cleaner

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps users analyze, clean, and prepare datasets by detecting data types, identifying data quality issues, and applying corrections automatically, reducing manual data wrangling and speeding up data work.

Core Features & Use Cases

  • Column Analysis: List all columns with basic statistics and sample values to understand dataset structure.
  • Type Detection: Automatically detect data types (numeric, categorical, ordinal, text, datetime, boolean) to guide cleaning.
  • Data Quality Reports: Generate completeness and quality insights to prioritize fixes.
  • Value Mapping & Cleaning: Auto-generate standardization mappings and apply cleaning rules to correct inconsistencies.
  • Use Case: You have a messy customer dataset with inconsistent category labels and missing values. This skill analyzes, cleans, and validates data, returning a clean dataset and a quality report.

Quick Start

Use the Data Cleaner skill to analyze and clean a dataset. Steps:

  • Run data exploration with the Analyze Columns and Detect Types scripts
  • Generate a quality report with data_quality_report.py
  • Apply value mappings and cleaning operations with clean_values.py
  • Validate the results with validation_report.py

Frequently Asked Questions about Data Cleaner

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

FAQPage Schema
How do I automatically detect data types in a CSV or Excel file?

Data Cleaner automatically detects data types—numeric, categorical, ordinal, text, datetime, boolean—across all columns in CSV, Excel, JSON, and JSONL files. Run the type detection script to classify each column and guide your cleaning strategy.

What's the best way to clean inconsistent values in a dataset?

Generate value mappings with Data Cleaner to identify inconsistencies, then apply standardization rules automatically. The skill produces a cleaned dataset and validation report, reducing manual correction work across large tables.

How do I generate a data quality report for my dataset?

Data Cleaner analyzes completeness and quality metrics across all columns, generating a quality report that highlights missing values, inconsistencies, and data issues. Use this report to prioritize which columns need cleaning first.

Can I use Data Cleaner with pandas and numpy workflows?

Yes. Data Cleaner integrates with pandas and numpy—the core dependencies—and works with tabular data in CSV, Excel, JSON, and JSONL formats. Reproducible execution runs via uv-managed Python scripts.

What columns and statistics does the column analysis provide?

Column analysis lists all columns with basic statistics and sample values to understand dataset structure. This step precedes type detection and helps identify which columns need attention before cleaning.

Do I need to validate results after running the cleaning operations?

Yes. Data Cleaner includes validation reporting to confirm that cleaning operations succeeded and data quality improved. Run the validation script after applying cleaning rules to verify the output dataset.