data cleaning and normalization

Use this skill when the user wants messy-data questions where the agent has to clean first and analyze later. Trigger it for requests such as “make it handle dirty columns,” “make it find bad rows,” “make it normalize before computing,” or “ask something where cleaning is the key move.” Plain-language examples: “Give me a question with outliers,” “make it fix formatting or missing data first,” “make it preprocess before answering.”