CSV Data Analyzer
A skill that enables Claw to load, explore, analyze, and visualize CSV datasets, providing statistical insights and answering questions about the data.
What This Skill Does
This skill equips Claw with a structured approach to CSV data analysis:
- Data Loading & Inspection — Read CSV files, detect column types, and display basic structure (shape, columns, sample rows)
- Data Cleaning — Identify and handle missing values, duplicates, and type inconsistencies
- Statistical Summary — Compute descriptive statistics (mean, median, mode, standard deviation, percentiles) for numeric columns
- Filtering & Grouping — Slice data by conditions and aggregate by categories
- Correlation Analysis — Find relationships between numeric variables
- Visualization — Generate charts (bar, line, scatter, histogram) to illustrate patterns
How to Use
Provide a CSV file and ask Claw to analyze it:
- "Analyze this sales data and tell me which product category has the highest revenue"
- "Find outliers in the temperature column of this dataset"
- "Create a chart showing monthly trends from this CSV"
- "Compare group A vs group B performance in this experiment data"
Requirements
- Input must be a valid CSV file (comma-separated by default; other delimiters can be specified)
- Python with pandas and matplotlib should be available in the environment
Output
- Summary statistics table
- Key insights in plain language
- Charts saved as PNG files when visualization is requested
- Cleaned dataset exported as a new CSV if data cleaning was performed
1---2name: ub2-csv-data-analyzer3description: CSV Data Analyzer4---5# CSV Data Analyzer67A skill that enables Claw to load, explore, analyze, and visualize CSV datasets, providing statistical insights and answering questions about the data.89## What This Skill Does1011This skill equips Claw with a structured approach to CSV data analysis:12131. **Data Loading & Inspection** — Read CSV files, detect column types, and display basic structure (shape, columns, sample rows)142. **Data Cleaning** — Identify and handle missing values, duplicates, and type inconsistencies153. **Statistical Summary** — Compute descriptive statistics (mean, median, mode, standard deviation, percentiles) for numeric columns164. **Filtering & Grouping** — Slice data by conditions and aggregate by categories175. **Correlation Analysis** — Find relationships between numeric variables186. **Visualization** — Generate charts (bar, line, scatter, histogram) to illustrate patterns1920## How to Use2122Provide a CSV file and ask Claw to analyze it:2324- "Analyze this sales data and tell me which product category has the highest revenue"25- "Find outliers in the temperature column of this dataset"26- "Create a chart showing monthly trends from this CSV"27- "Compare group A vs group B performance in this experiment data"2829## Requirements3031- Input must be a valid CSV file (comma-separated by default; other delimiters can be specified)32- Python with pandas and matplotlib should be available in the environment3334## Output3536- Summary statistics table37- Key insights in plain language38- Charts saved as PNG files when visualization is requested39- Cleaned dataset exported as a new CSV if data cleaning was performed
javimosch