skill-name

aRustyDev's avatarfrom aRustyDev

{{DESCRIPTION}}

⭐1stars🔀1forks📁View on GitHub🕐Updated Jan 4, 2026
[Data Cleaning]

When & Why to Use This Skill

This Claude skill automates the tedious process of data preprocessing by identifying and resolving inconsistencies, missing values, and formatting errors in Python datasets. It leverages Pandas and NumPy best practices to transform raw, messy data into analysis-ready formats, significantly reducing the time spent on data preparation for data scientists and analysts.

Use Cases

  • Automated Outlier Detection: Identify and handle statistical anomalies in large datasets to prevent skewed analysis results.
  • Format Standardization: Convert disparate date formats, currency strings, and categorical labels into a unified schema across multiple data sources.
  • Missing Value Imputation: Apply intelligent strategies (mean, median, or predictive modeling) to fill gaps in datasets while maintaining statistical integrity.
name{{SKILL_NAME}}
description{{DESCRIPTION}}
created{{CREATED_DATE}}
updated{{UPDATED_DATE}}
tags[{{CATEGORY}}, {{SUBCATEGORY}}, {{TOOL}}, {{FOCUS}}]
source{{SOURCE_REPO}}

{{TITLE}}

{{ONE_LINE_DESCRIPTION}}

Overview

{{OVERVIEW_TEXT}}

This skill covers:

  • {{COVERAGE_ITEM_1}}
  • {{COVERAGE_ITEM_2}}
  • {{COVERAGE_ITEM_3}}

This skill does NOT cover:

  • {{EXCLUSION_ITEM_1}}
  • {{EXCLUSION_ITEM_2}}

Quick Reference

Key Commands

Command Description
{{CMD_1}} {{CMD_1_DESC}}
{{CMD_2}} {{CMD_2_DESC}}

Common Patterns

Pattern When to Use
{{PATTERN_1}} {{PATTERN_1_USE}}
{{PATTERN_2}} {{PATTERN_2_USE}}

Workflow: {{PRIMARY_WORKFLOW}}

Step 1: {{STEP_1_TITLE}}

{{STEP_1_CONTENT}}

Step 2: {{STEP_2_TITLE}}

{{STEP_2_CONTENT}}

Step 3: {{STEP_3_TITLE}}

{{STEP_3_CONTENT}}

Common Patterns

{{PATTERN_SECTION_1}}

{{CODE_EXAMPLE_1}}

{{PATTERN_SECTION_2}}

{{CODE_EXAMPLE_2}}

Troubleshooting

{{ISSUE_1}}

Symptoms: {{SYMPTOMS_1}}

Solution: {{SOLUTION_1}}

{{ISSUE_2}}

Symptoms: {{SYMPTOMS_2}}

Solution: {{SOLUTION_2}}

See Also