Csv Data Summarizer

1---2name: csv-data-summarizer3description: Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.4metadata:5  version: 2.1.06  dependencies: python>=3.8, pandas>=2.0.0, matplotlib>=3.7.0, seaborn>=0.12.07---8 9# CSV Data Summarizer10 11This Skill analyzes CSV files and provides comprehensive summaries with statistical insights and visualizations.12 13## When to Use This Skill14 15Claude should use this Skill whenever the user:16- Uploads or references a CSV file17- Asks to summarize, analyze, or visualize tabular data18- Requests insights from CSV data19- Wants to understand data structure and quality20 21## How It Works22 23## ⚠️ CRITICAL BEHAVIOR REQUIREMENT ⚠️24 25**DO NOT ASK THE USER WHAT THEY WANT TO DO WITH THE DATA.**26**DO NOT OFFER OPTIONS OR CHOICES.**27**DO NOT SAY "What would you like me to help you with?"**28**DO NOT LIST POSSIBLE ANALYSES.**29 30**IMMEDIATELY AND AUTOMATICALLY:**311. Run the comprehensive analysis322. Generate ALL relevant visualizations333. Present complete results344. NO questions, NO options, NO waiting for user input35 36**THE USER WANTS A FULL ANALYSIS RIGHT AWAY - JUST DO IT.**37 38### Automatic Analysis Steps:39 40**The skill intelligently adapts to different data types and industries by inspecting the data first, then determining what analyses are most relevant.**41 421. **Load and inspect** the CSV file into pandas DataFrame432. **Identify data structure** - column types, date columns, numeric columns, categories443. **Determine relevant analyses** based on what's actually in the data:45   - **Sales/E-commerce data** (order dates, revenue, products): Time-series trends, revenue analysis, product performance46   - **Customer data** (demographics, segments, regions): Distribution analysis, segmentation, geographic patterns47   - **Financial data** (transactions, amounts, dates): Trend analysis, statistical summaries, correlations48   - **Operational data** (timestamps, metrics, status): Time-series, performance metrics, distributions49   - **Survey data** (categorical responses, ratings): Frequency analysis, cross-tabulations, distributions50   - **Generic tabular data**: Adapts based on column types found51 524. **Only create visualizations that make sense** for the specific dataset:53   - Time-series plots ONLY if date/timestamp columns exist54   - Correlation heatmaps ONLY if multiple numeric columns exist55   - Category distributions ONLY if categorical columns exist56   - Histograms for numeric distributions when relevant57   585. **Generate comprehensive output** automatically including:59   - Data overview (rows, columns, types)60   - Key statistics and metrics relevant to the data type61   - Missing data analysis62   - Multiple relevant visualizations (only those that apply)63   - Actionable insights based on patterns found in THIS specific dataset64   656. **Present everything** in one complete analysis - no follow-up questions66 67**Example adaptations:**68- Healthcare data with patient IDs → Focus on demographics, treatment patterns, temporal trends69- Inventory data with stock levels → Focus on quantity distributions, reorder patterns, SKU analysis  70- Web analytics with timestamps → Focus on traffic patterns, conversion metrics, time-of-day analysis71- Survey responses → Focus on response distributions, demographic breakdowns, sentiment patterns72 73### Behavior Guidelines74 75✅ **CORRECT APPROACH - SAY THIS:**76- "I'll analyze this data comprehensively right now."77- "Here's the complete analysis with visualizations:"78- "I've identified this as [type] data and generated relevant insights:"79- Then IMMEDIATELY show the full analysis80 81✅ **DO:**82- Immediately run the analysis script83- Generate ALL relevant charts automatically84- Provide complete insights without being asked85- Be thorough and complete in first response86- Act decisively without asking permission87 88❌ **NEVER SAY THESE PHRASES:**89- "What would you like to do with this data?"90- "What would you like me to help you with?"91- "Here are some common options:"92- "Let me know what you'd like help with"93- "I can create a comprehensive analysis if you'd like!"94- Any sentence ending with "?" asking for user direction95- Any list of options or choices96- Any conditional "I can do X if you want"97 98❌ **FORBIDDEN BEHAVIORS:**99- Asking what the user wants100- Listing options for the user to choose from101- Waiting for user direction before analyzing102- Providing partial analysis that requires follow-up103- Describing what you COULD do instead of DOING it104 105### Usage106 107The Skill provides a Python function `summarize_csv(file_path)` that:108- Accepts a path to a CSV file109- Returns a comprehensive text summary with statistics110- Generates multiple visualizations automatically based on data structure111 112### Example Prompts113 114> "Here's `sales_data.csv`. Can you summarize this file?"115 116> "Analyze this customer data CSV and show me trends."117 118> "What insights can you find in `orders.csv`?"119 120### Example Output121 122**Dataset Overview**123- 5,000 rows × 8 columns  124- 3 numeric columns, 1 date column  125 126**Summary Statistics**127- Average order value: $58.2  128- Standard deviation: $12.4129- Missing values: 2% (100 cells)130 131**Insights**132- Sales show upward trend over time133- Peak activity in Q4134*(Attached: trend plot)*135 136## Files137 138- `analyze.py` - Core analysis logic139- `requirements.txt` - Python dependencies140- `resources/sample.csv` - Example dataset for testing141- `resources/README.md` - Additional documentation142 143## Notes144 145- Automatically detects date columns (columns containing 'date' in name)146- Handles missing data gracefully147- Generates visualizations only when date columns are present148- All numeric columns are included in statistical summary