{
  "skill_name": "observability-plan",
  "evals": [
    {
      "id": 1,
      "prompt": "Design the observability plan for our checkout service — what should we measure, alert on, and page for?",
      "assertions": [
        "SLIs measure user experience as good-over-valid events, not resource utilization",
        "Latency SLIs are threshold counts at a percentile, never averages",
        "Every SLO carries an error budget stated in human terms plus a policy for when it is spent",
        "Pages are symptom-based, actionable, and runbook-linked; anything not actionable is a ticket, not a page",
        "The plan makes a deliberate metrics-vs-logs-vs-traces choice rather than proposing everything"
      ]
    }
  ]
}