Help the user choose, create, iterate, or align MLflow judges and scorers for an agent, RAG app, LLM app, or GenAI workflow, including MemAlign and domain-expert labels. Build a small set of atomic quality criteria with the cheapest reliable implementation.
Install
npx skills add mlflow/skills --skill build-a-scorernpx skills add mlflow/skills --skill build-a-scorer -a claude-code -gnpx skills add mlflow/skills --skill build-a-scorer -a codex -ggemini skills install https://github.com/mlflow/skills.git --path build-a-scorergh skill install mlflow/skills build-a-scorergit clone --depth 1 https://github.com/mlflow/skills /tmp/mlflow__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mlflow__skills/build-a-scorer ~/.claude/skills/build-a-scorer # Claude Code
cp -R /tmp/mlflow__skills/build-a-scorer ~/.agents/skills/build-a-scorer # Codex, Cursor, Gemini CLI, Copilot, OpenCode