MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt…
安装
npx skills add databricks/databricks-agent-skills --skill databricks-mlflow-evaluationnpx skills add databricks/databricks-agent-skills --skill databricks-mlflow-evaluation -a claude-code -gnpx skills add databricks/databricks-agent-skills --skill databricks-mlflow-evaluation -a codex -ggemini skills install https://github.com/databricks/databricks-agent-skills.git --path skills/databricks-mlflow-evaluationgh skill install databricks/databricks-agent-skills databricks-mlflow-evaluationgit clone --depth 1 https://github.com/databricks/databricks-agent-skills /tmp/databricks__databricks-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/databricks__databricks-agent-skills/skills/databricks-mlflow-evaluation ~/.claude/skills/databricks-mlflow-evaluation # Claude Code
cp -R /tmp/databricks__databricks-agent-skills/skills/databricks-mlflow-evaluation ~/.agents/skills/databricks-mlflow-evaluation # Codex, Cursor, Gemini CLI, Copilot, OpenCode