Agent Ops

This skill should be used when the user asks about agent architecture, evaluation, metrics, production monitoring, debugging agents, or best practices for building reliable AI agents. Use for questions like "evaluate my agent", "set up production monitoring", "add guardrails", "detect hallucinations", "agent anti-patterns", "compare experiments", "create evaluation dataset".

comet-ml Updated 23.4k repo stars
How Tracing Works

File contents

comet-ml/opik-claude-code-plugin commit a88cde6953 Runs: comet-ml/opik

Frequently asked questions

npx get-skill add comet-ml/agent-ops