Does it handle dirty data or missing values?

Yes, it includes a dedicated missing data analysis step and handles null values gracefully to ensure statistical accuracy even with incomplete datasets.

How does the skill decide which visualizations to create?

It intelligently inspects your data structure; it only generates time-series plots if date columns are detected and correlation heatmaps if multiple numeric columns exist, ensuring visualizations are always relevant.

Can I request specific analyses after the initial summary?

While the skill is designed to provide a comprehensive analysis immediately, you can still ask follow-up questions to Claude to dive deeper into specific patterns identified in the summary.

Do I need to specify the data category, such as 'Finance' or 'Sales'?

No, the skill automatically detects the nature of the data by analyzing column headers and content, adapting its insights to fit the specific domain of your dataset.

What Python libraries are required for this skill?

The skill utilizes industry-standard libraries including pandas for data processing, and Matplotlib and Seaborn for generating professional visualizations.

CSV Data Summarizer

Name: CSV Data Summarizer
Author: kivilaid

bykivilaid

•

データサイエンスとML

Analyzes CSV files automatically to generate comprehensive statistical summaries and tailored visualizations using Python and pandas.

概要

The CSV Data Summarizer is a high-efficiency Claude Code Skill designed to provide instant exploratory data analysis without requiring user prompts or configuration. Upon detecting a CSV file, it intelligently identifies the data structure—such as sales, financial, or customer data—and automatically executes relevant statistical tests, missing value audits, and visual plots. By leveraging Python's data science ecosystem, it transforms raw tabular data into actionable insights and professional charts immediately, making it ideal for developers and data scientists who need rapid visibility into their datasets during the development workflow.

主な機能

Automated visualization suite using Matplotlib and Seaborn
Comprehensive data quality and missing value analysis
Instant generation of industry-specific statistical summaries
Zero-interaction execution that delivers results without follow-up questions
Autonomous data type detection (Temporal, Categorical, and Numerical)
6 GitHub stars

ユースケース

Rapidly auditing new datasets to understand structure and quality issues
Generating instant sales or financial trend reports from transaction logs
Performing quick exploratory data analysis (EDA) during a coding session

概要

主な機能

Automated visualization suite using Matplotlib and Seaborn
Comprehensive data quality and missing value analysis
Instant generation of industry-specific statistical summaries
Zero-interaction execution that delivers results without follow-up questions
Autonomous data type detection (Temporal, Categorical, and Numerical)
6 GitHub stars

ユースケース

Rapidly auditing new datasets to understand structure and quality issues
Generating instant sales or financial trend reports from transaction logs
Performing quick exploratory data analysis (EDA) during a coding session