Can it handle datasets with missing or messy data?

Yes, it includes a built-in data quality check that identifies missing values and handles them gracefully during the statistical calculation process.

Does this skill require user input to start the analysis?

No, it follows a strict behavior requirement to immediately and automatically run a full analysis as soon as a CSV file is detected, providing results without asking follow-up questions.

How does the skill know which analysis to run?

The skill inspects column headers, data types, and value distributions to automatically identify the dataset category (such as e-commerce, financial, or healthcare) and applies relevant analysis patterns.

Which Python libraries are used for the visualizations?

The skill utilizes the pandas library for data processing, while matplotlib and seaborn are used to generate professional-grade charts and heatmaps.

Automatic CSV Data Analyst

Name: Automatic CSV Data Analyst
Author: Jst-Well-Dan

byJst-Well-Dan

데이터 과학 및 ML

Analyzes CSV files automatically to provide statistical summaries, domain-specific insights, and relevant visualizations without requiring user intervention.

소개

The CSV Data Summarizer is a specialized Claude Code skill designed for high-velocity data exploration and business intelligence. It eliminates the back-and-forth of traditional data analysis by automatically detecting the structure and domain of your dataset—whether it's sales, customer demographics, financial transactions, or operational metrics. Upon referencing a CSV, the skill immediately performs a comprehensive audit, generates relevant statistical metrics, and creates high-quality visualizations like time-series plots and correlation heatmaps, delivering finished results and actionable insights in a single response.

주요 기능

Domain-aware insight extraction for e-commerce, finance, and more
Comprehensive statistical auditing and missing data analysis
Automatic industry-specific data type detection
Zero-prompt execution for instant data summaries
0 GitHub stars
Dynamic visualization generation using Matplotlib and Seaborn

사용 사례

Generating immediate visual sales reports from raw transaction logs
Auditing data quality and identifying missing values in large CSV files
Performing instant exploratory data analysis (EDA) on new datasets

소개

주요 기능

Domain-aware insight extraction for e-commerce, finance, and more
Comprehensive statistical auditing and missing data analysis
Automatic industry-specific data type detection
Zero-prompt execution for instant data summaries
0 GitHub stars
Dynamic visualization generation using Matplotlib and Seaborn

사용 사례

Generating immediate visual sales reports from raw transaction logs
Auditing data quality and identifying missing values in large CSV files
Performing instant exploratory data analysis (EDA) on new datasets