{
  "skill_name": "agent-loop-design",
  "evals": [
    {
      "id": 1,
      "prompt": "Design an agent loop that keeps our API reference docs in sync with the codebase: when endpoints change, the agent should update the docs, and we want to review before anything is published to the public docs site.",
      "assertions": [
        "One run's artifact and an observable done-condition are named (not 'docs look correct')",
        "The state machine has exactly generate/verify/gate(/escalate) states, rendered as valid Mermaid stateDiagram-v2",
        "The verifier is structurally different from the generator, with the independence stated",
        "Both caps are numbers: a revision cap and a per-run budget line",
        "Publishing to the public docs site sits behind a human gate with a decision-shaped digest format described",
        "Findings from a failed verify flow into the next generate round explicitly",
        "All three failure routes are specified: cap-hit escalation with digest, can't-judge BLOCKED route, systemic early-stop",
        "A telemetry row logs rounds/spend/verdict per run with a review cadence",
        "Hand-offs point to subagent-design for fan-out and agent-budget for the spend model"
      ]
    },
    {
      "id": 2,
      "prompt": "[Non-interactive run — no user available to answer questions] Design an agent loop.",
      "assertions": [
        "No loop is designed — the output is BLOCKED: need the task and its done-condition",
        "No state machine or caps are fabricated"
      ]
    }
  ]
}