Fix or change an AI agent's behavior using MLflow traces and regression tests. Use for wrong or incomplete answers, hallucinations, missing tool calls, new business rules, trace-driven debugging, or context and token-cost optimization. Diagnose the actual failure, plan a test, implement the smallest fix, and verify the new behavior without breaking existing cases.
Install
npx skills add mlflow/skills --skill fix-agent-issuenpx skills add mlflow/skills --skill fix-agent-issue -a claude-code -gnpx skills add mlflow/skills --skill fix-agent-issue -a codex -ggemini skills install https://github.com/mlflow/skills.git --path fix-agent-issuegh skill install mlflow/skills fix-agent-issuegit clone --depth 1 https://github.com/mlflow/skills /tmp/mlflow__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mlflow__skills/fix-agent-issue ~/.claude/skills/fix-agent-issue # Claude Code
cp -R /tmp/mlflow__skills/fix-agent-issue ~/.agents/skills/fix-agent-issue # Codex, Cursor, Gemini CLI, Copilot, OpenCode