What problem does it solve? Analysts querying semantic models often produce silently wrong results: fan-out from joins inflates aggregates, mismatched filter values return zero rows, and nulls distort averages. This Skill provides a checklist of common pitfalls to catch these errors before presenting an answer. ## Core Features & Use Cases - Query Construction Checks: Covers wrong grain and fan-out, invented field names, mismatched filter values, missing filters, misinterpreted entities, fragile ad-hoc definitions, and hidden filters in views. - Result Interpretation Checks: Flags implausible magnitudes, nulls distorting aggregations, count vs. count distinct confusion, ambiguous percentage denominators, and time period mismatches. - Verification Signals: Validates that parts sum to the whole, row counts make sense, and zero-row results are investigated rather than reported as missing data. - Use Case: After running a Malloy query breaking down revenue by region, use this checklist to confirm the regional totals sum to the overall total and that no join fan-out inflated the numbers. ## Quick Start Review my Malloy query and its results against the analysis pitfalls checklist before I present the answer.
