Before writing any analysis code on a new dataset.
Here is a description of my dataset and its known issues: [paste]. Propose a cleaning strategy: what to check, how to handle missing values, and what to log for reproducibility.
Anything in square brackets is meant to be replaced. The builder turns those into fields you can type into.
Tired of re-pasting the same context into every new chat? That is what the Unimatrix MCP server is for.