{
  "skill_name": "launch-readiness",
  "evals": [
    {
      "id": 1,
      "prompt": "Are we ready to launch? PR #412 adds a `loyalty_points` column to `customers`, backfills it from order history, and shows points on the checkout page. Going to 100% of users Thursday. Load test hit p99 180ms against a 250ms target (link: grafana/d/lt-412). We have a dashboard but haven't added alerts yet. Support hasn't been told.",
      "assertions": [
        "Lists 3-5 failure modes specific to this change (e.g. backfill load on customers, wrong point totals shown at checkout) before the checklist",
        "Every check row has a status of met, not met, or n/a with a reason, plus an evidence column and an owner expressed as a role",
        "Rollback is the first row and is not met, because no tested rollback or data story was supplied",
        "Detection is not met because no alerts exist, and the report hands off to observability-plan rather than drafting the alert inline",
        "The quality-targets row is met and cites the supplied load-test link as evidence",
        "Exposure is flagged because a 100% launch is not staged and no reason is given for why all-at-once is safe",
        "The verdict is BLOCKED, and the reason given is the missing rollback",
        "No dashboards, test results, or sign-offs are invented beyond what the prompt supplied"
      ]
    }
  ]
}