coffeefuelbump/csv-data-summarizer-claude-skill

Overview

This skill analyzes uploaded CSV files end-to-end and returns a complete, ready-to-read summary with statistics and visualizations. It is implemented in Python using pandas and plotting libraries to detect structure, assess data quality, and surface actionable insights automatically.

How this skill works

The skill loads the CSV into a pandas DataFrame, infers column types (numeric, categorical, datetime), and scans for missing values and outliers. It then automatically selects and generates only the visualizations that apply to the detected columns (time-series plots for dates, histograms for numeric fields, category distributions, correlation heatmaps, etc.). Finally, it compiles a single comprehensive report with data overview, key metrics, missing-data diagnostics, charts, and concise insights.

When to use it

• When you upload or reference any CSV and want a full analysis immediately.
• To get a quick data-quality check and missing-value summary without manual steps.
• To explore time trends, distributions, and correlations in tabular datasets.
• When preparing a dataset for modeling or reporting and you need descriptive stats.
• To produce fast visualizations for presentations or exploratory analysis.

Best practices

• Provide the raw CSV file; the tool inspects the file automatically and runs the full analysis.
• Ensure date columns are clearly named (containing 'date') for optimal time-series detection.
• Keep categorical labels consistent (avoid mixed types) to improve distribution summaries.
• Use reasonable file sizes (thousands to low millions of rows) for interactive runtimes.
• Review generated visuals and the summary to guide any downstream cleaning or feature work.

Example use cases

• Summarize an orders.csv to get order counts, average order value, and revenue trends by date.
• Inspect customer.csv to understand demographic distributions, missing contact info, and segments.
• Analyze transactions.csv for spending patterns, outlier transactions, and month-over-month trends.
• Quickly assess survey results.csv for response frequency, rating distributions, and cross-tabs.
• Validate inventory.csv to find low-stock SKUs, quantity distributions, and reorder signals.