Tabular EDA Review

Use this skill for CSV, dataset, EDA, feature, model-input, or data-quality tasks in this workspace.

Workflow

1. Read AGENTS.md.
2. Load relevant dataset facts from Serena memories first. If Serena is unavailable, use docs/memory-bank/.
3. Identify the dataset path and task goal.
4. Inspect headers, shape, dtypes, missingness, unique counts for key columns, target column, and obvious join keys.
5. Identify leakage risks, ID columns, demographic fields, target imbalance, train/test mismatch, and columns needing encoding or scaling.
6. Recommend the smallest next action: cleaning, validation, visualization, baseline model, or submission check.

Safety