Update to SQL Copilot

{
  "description": "Write SQL from natural-language specifications with explicit grain, keys and acceptance checks.",
  "included_files": [],
  "name": "sql-from-requirements",
  "skill_md_contents": "---\nname: sql-from-requirements\ndescription: Write SQL from natural-language specifications with explicit grain, keys and acceptance checks.\n---\n\n# Sql From Requirements\n\n**Trigger:** Write SQL from natural-language specifications with explicit grain, keys and acceptance checks.\n\n## Workflow\n1. Convert the requirement into a small input/output contract: tables, columns, filters, dates, keys, grouping, expected result grain, dialect.\n2. Sketch cardinality before joining: which joins are one-to-one, one-to-many, or many-to-many? Pre-aggregate many-side measures where appropriate.\n3. Write one dialect-correct query; use explicit columns for production and clear CTE names based on meaning, not perceived optimizer behavior.\n4. Check NULL rules, inclusive/exclusive time bounds, time zones, ties, deterministic ordering, integer versus decimal arithmetic and potential duplication.\n5. Add validation SQL: duplicate-key count, total reconciliation or result-shape checks sized to the task; do not assert it ran.\n\n## Critical standard\nOutput grain and expected uniqueness must be explicit; explain assumptions instead of inventing schema.\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/query-specification.md` when relevant.\n- Read `../../references/correctness-and-grain.md` when relevant.\n- Read `../../references/dialects.md` when relevant.\n\n## Return\nOne copyable query, a concise meaning explanation, assumptions and 1–3 useful validation checks.\n"
}