Update to Software & AI Copilot

{
  "description": "Harden ML training, feature engineering, inference and evaluation code for reproducibility and safe production use.",
  "included_files": [],
  "name": "productionize-ml-code",
  "skill_md_contents": "---\nname: productionize-ml-code\ndescription: Harden ML training, feature engineering, inference and evaluation code for reproducibility and safe production use.\n---\n\n# Productionize Ml 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/ml-production.md` for detailed method when necessary.\n\n## Procedure\n1. Inspect training/inference contracts, feature provenance, data splits and leakage risks.\n2. Separate preprocessing, training, evaluation, inference and artifact versions.\n3. Add schema checks, reproducible configurations, slice evaluations and meaningful baseline tests.\n4. Check train/serve skew, serialization, resource needs and fallback behavior.\n5. Report observed metrics only; provide an evaluation plan when data/runtime are missing.\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"
}