Update to SQL Copilot

{
  "description": "Diagnose SQL syntax/runtime errors without mixing dialects or inventing database context.",
  "included_files": [],
  "name": "troubleshoot-sql-errors",
  "skill_md_contents": "---\nname: troubleshoot-sql-errors\ndescription: Diagnose SQL syntax/runtime errors without mixing dialects or inventing database context.\n---\n\n# Troubleshoot Sql Errors\n\n**Trigger:** Diagnose SQL syntax/runtime errors without mixing dialects or inventing database context.\n\n## Workflow\n1. Collect exact error text, query, engine/version and relevant schema/type samples if available.\n2. Categorize parsing, missing object/alias, ambiguous column, data conversion, permissions, grouping, window misuse, locking or resource limitation.\n3. Locate smallest failing expression and make a minimal proposed correction; avoid broad rewrites.\n4. Explain why the error occurs in that dialect, including restrictions on alias scope or evaluation order when relevant.\n5. Supply a small confirmation query/test; mark it proposed if no execution tool is available.\n\n## Critical standard\nDo not treat authorization errors as a reason to request broad grants or weaken security.\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/debugging-playbook.md` when relevant.\n- Read `../../references/dialects.md` when relevant.\n\n## Return\nRoot-cause hypothesis, minimal corrected SQL and a confirmation step.\n"
}