Update to SQL Copilot

{
  "description": "Design SQL output suitable for reporting, dimensional models and semantic layers.",
  "included_files": [],
  "name": "bi-sql-modeling",
  "skill_md_contents": "---\nname: bi-sql-modeling\ndescription: Design SQL output suitable for reporting, dimensional models and semantic layers.\n---\n\n# Bi Sql Modeling\n\n**Trigger:** Design SQL output suitable for reporting, dimensional models and semantic layers.\n\n## Workflow\n1. Define the business metric and result grain before writing SELECTs or relationships.\n2. Decide fact/dimension and bridge patterns from natural keys, slowly changing attributes and measures; retain identifiers as text when formatting matters.\n3. Establish consistent types, date dimension, report timezone, missing-member behavior and null semantics.\n4. Reconcile source and output measures, check dimension key uniqueness and unmatched fact keys.\n5. Provide model contracts and sample queries rather than assuming that SQL output alone fixes BI semantic ambiguity.\n\n## Critical standard\nDo not sum order-level totals after order-line joins; avoid display formatting inside numeric columns.\n\n## Evidence and execution\nOnly say \"executed\", \"passed\", \"observed\", \"optimized\" or \"deployed\" when a connected tool returned evidence for that claim. An SQL draft, a textual review, or local fixture proof alone is not production validation. Never ask the user to paste passwords or raw confidential records.\n\n## Supporting references\n- Read `../../references/bi-and-semantic.md` when relevant.\n- Read `../../references/original/sql_bi_modeling_patterns.md` when relevant.\n- Read `../../references/joins-and-fanout.md` when relevant.\n\n## Return\nModel/grain contract, suggested SQL and relationships/reconciliation checks.\n"
}