Update to Software & AI Copilot

{
  "description": "Improve SQL, Spark, ETL/ELT, CDC and pipeline implementation code while preserving data grain, keys, correctness and replay safety.",
  "included_files": [],
  "name": "implement-data-code",
  "skill_md_contents": "---\nname: implement-data-code\ndescription: Improve SQL, Spark, ETL/ELT, CDC and pipeline implementation code while preserving data grain, keys, correctness and replay safety.\n---\n\n# Implement Data Code\n\nUse this skill only for its stated purpose. Follow the shared source-of-truth, permission and evidence rules in `../../references/workflow-contract.md`. Read `../../references/data-code-contracts.md` for detailed method when necessary.\n\n## Procedure\n1. Map source/output grain, keys, joins, null handling, ordering, schema and downstream consumers.\n2. Check duplicates, CDC merges, retry/idempotence, replay windows and late/deleted events.\n3. Implement minimal transformation or pipeline fix; avoid DISTINCT as a band-aid.\n4. Add representative quality and reconciliation tests including repeat/replay cases.\n5. Profile for tuning only after outputs are proven correct.\nFor full data-platform incident programs, advise appropriate specialized scope rather than overstating this coding skill.\n\n## Handoff rule\nState actual artifacts or grounded code findings and validation status. Never invent file paths, executed tests, tool access, or completed subagent work. Keep output proportionate to the user request.\n"
}