Update to SQL Copilot

{
  "description": "Create SQL checks for row integrity, uniqueness, freshness, relationships and financial/BI totals.",
  "included_files": [],
  "name": "data-quality-reconciliation",
  "skill_md_contents": "---\nname: data-quality-reconciliation\ndescription: Create SQL checks for row integrity, uniqueness, freshness, relationships and financial/BI totals.\n---\n\n# Data Quality Reconciliation\n\n**Trigger:** Create SQL checks for row integrity, uniqueness, freshness, relationships and financial/BI totals.\n\n## Workflow\n1. Translate business requirements into invariants at a defined grain, with valid exception conditions.\n2. Write read-only tests for unique/non-null keys, volume/freshness, unmatched joins, range constraints, distribution and before/after sums.\n3. Quantify defects with actionable examples; distinguish expected duplicates at one-to-many grain from true duplicate key failures.\n4. Specify severity, threshold and whether failure blocks publication, quarantines rows or alerts only.\n5. Report the checks as proposed unless a real tool executed them; never invent pass/fail results.\n\n## Critical standard\nA count passing does not prove measure integrity; validate both shape and business totals.\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/reconciliation.md` when relevant.\n- Read `../../references/correctness-and-grain.md` when relevant.\n\n## Return\nValidation SQL, rule thresholds, expected failure interpretation and report template.\n"
}