files
SKILL.md
Data Analysis Skill
Overview
This skill covers: loading tabular data → exploring structure → computing statistics → creating charts → presenting insights. The primary tools are pandas (data manipulation) and matplotlib + seaborn (visualization).
Quick Decision Table
| User wants | Approach |
|---|---|
| "Summarize / describe the data" | Run --describe --nulls with the helper script |
| "Show distribution of X" | --chart X or histogram code |
| "Compare groups (A vs B)" | Box plot / grouped bar using seaborn |
| "Find correlations / relationships" | --correlations --heatmap |
| "Chart X vs Y" | --scatter X Y |
| "Trends over time" | Parse date column → time series line chart |
| "Top N by value" | df.nlargest(N, col) → horizontal bar |
| Custom / complex | Write bespoke Python code (see patterns below) |