csv-data-summarizer

CSV Data Analyzer

This skill analyzes CSV files and provides a comprehensive summary containing statistical insights and visualizations.

When to Use This Skill

When the user:

• Uploads or mentions a CSV file
• Requests summary, analysis, or visualization of tabular data
• Requests insights from CSV data
• Wants to understand data structure and quality

How It Works

⚠️ Critical Behavior Requirements ⚠️

Do not ask the user what they want to do with the data. Do not offer options or choices. Do not say "What would you like me to help you with?" Do not list possible analysis options.

Immediately and automatically execute:

1. Run comprehensive analysis
2. Generate all relevant visualizations
3. Show complete results
4. No questions, no options, no waiting for user input

The user wants to immediately get a complete analysis - just do it directly.

Automatic analysis steps:

This skill intelligently adapts to different data types and industries by first inspecting the data, then determining the most relevant analysis.

1. Load and inspect CSV file into a pandas DataFrame

2. Identify data structure - column types, date columns, numeric columns, categories

3. Determine relevant analysis based on data content：

   • Sales/e-commerce data(order date, revenue, product): time series trends, revenue analysis, product performance
   • Customer data(demographics, segmentation, region): distribution analysis, segmentation, geographic patterns
   • Financial data(transactions, amounts, dates): trend analysis, statistical summary, correlation
   • Operations data(timestamps, metrics, status): time series, performance metrics, distribution
   • Survey data(categorical responses, ratings): frequency analysis, cross-tabulation, distribution
   • General tabular data: adjust based on the column types found

4. Create only visualizations that are meaningful for the specific dataset：

   • Time series charts only when a date/timestamp column exists
   • Correlation heatmaps only when multiple numeric columns exist
   • Category distribution only when categorical columns exist
   • Histograms of numeric distributions (when relevant)

5. Automatically generate comprehensive outputincluding:

   • Data overview (number of rows, number of columns, types)
   • Key statistics and metrics relevant to the data type
   • Missing data analysis
   • Multiple relevant visualizations (only those that apply)
   • Actionable insights based on patterns found in this specific dataset

6. Show everything at once - do not follow up with questions

Adaptation examples:

• Healthcare data with patient IDs → focus on demographics, treatment patterns, time trends
• Inventory data with stock levels → focus on quantity distribution, restocking patterns, SKU analysis
• Website analytics with timestamps → Focus on traffic patterns, conversion metrics, time-period analysis
• Survey responses → Focus on response distribution, demographic segmentation, sentiment patterns

Behavioral Guidelines

✅ Correct Approach - Say This:

• "I am now conducting a comprehensive analysis of this data."
• "Here is the complete analysis with visualizations:"
• "I identified this as [type] data and generated relevant insights:"
• Then immediately present the complete analysis

✅ Do:

• Run the analysis script immediately
• Automatically generate all relevant charts
• Provide complete insights without asking
• Do it comprehensively and completely in the first response
• Act decisively without seeking permission

❌ Never say these things:

• "What would you like to do with this data?"
• "What would you like me to help you do?"
• "Here are some common options:"
• "Let me know what you would like help with"
• "If you'd like, I can create a comprehensive analysis!"
• Any sentence ending in "?" that asks the user for direction
• Any list of options or choices
• Any conditional "if you want, I can do X"

❌ Prohibited Behaviors:

• Asking the user what they want
• Listing options for the user to choose from
• Waiting for user instructions before analyzing
• Providing partial analysis that requires follow-up
• Describing what you can do instead of just doing it

Usage

This skill provides a Python function summarize_csv(file_path)：

• Accepts the path to a CSV file
• Returns a comprehensive text summary with statistical information
• Automatically generates multiple visualizations based on the data structure

Example prompts

"This is sales_data.csv. Can you summarize this file?"

"Analyze this customer data CSV and show trends."

"What insights can you discover from orders.csv ?"

Example output

Dataset Overview

• 5,000 rows × 8 columns
• 3 numerical columns, 1 date column

Statistical Summary

• Average order value: $58.2
• Standard deviation: $12.4
• Missing values: 2% (100 cells)

Insights

• Sales show an upward trend over time
• Q4 campaign reached its peak (attached: trend chart)

Files

• analyze.py - Core analysis logic
• requirements.txt - Python dependencies
• resources/sample.csv - Example dataset for testing
• resources/README.md - Additional documentation

Notes

• Automatically detects the date column (columns with 'date' in the name)
• Gracefully handles missing data
• Only generates visualizations when a date column exists
• All numerical columns are included in the statistical summary