{
  "skill_name": "plastic-roadmap-continuing",
  "notes": "Intent 158a1. New roadmap route, closing the gap that forced the 171 (consistency-dividend) roadmap handoff to be resumed by hand. Scopes: description triggering (1-3) and behavior/convention compliance (4-8), the latter checked against SKILL.md.",
  "results": {
    "triggering": { "cases": 3, "passed": 3, "run": "2026-07-10, one subagent per case" },
    "behavior": { "cases": 5, "passed": 5, "evidence": "convention checks against skills/roadmap-continuing/SKILL.md and references/liveness-ranking.md" }
  },
  "evals": [
    {
      "id": 1, "scope": "triggering", "set": "train",
      "prompt": "continue the roadmap",
      "expected_output": "Activates plastic-roadmap-continuing.",
      "files": [],
      "assertions": [
        { "type": "code", "check": "router CHOICE == plastic-roadmap-continuing", "observed": "plastic-roadmap-continuing", "result": "pass" }
      ]
    },
    {
      "id": 2, "scope": "triggering", "set": "train",
      "prompt": "resume the delivery batch we were shipping",
      "expected_output": "Activates plastic-roadmap-continuing.",
      "files": [],
      "assertions": [
        { "type": "code", "check": "router CHOICE == plastic-roadmap-continuing", "observed": "plastic-roadmap-continuing", "result": "pass" }
      ]
    },
    {
      "id": 3, "scope": "triggering", "set": "validation",
      "prompt": "where did that batch of intents land",
      "expected_output": "Activates plastic-roadmap-continuing (indirect trigger: a roadmap-resume request that never names 'roadmap' or 'continue').",
      "files": [],
      "assertions": [
        { "type": "code", "check": "router CHOICE == plastic-roadmap-continuing", "observed": "plastic-roadmap-continuing", "result": "pass" }
      ]
    },
    {
      "id": 4, "scope": "behavior", "set": "train",
      "prompt": "Does the skill rank liveness correctly when a batch entry is delivering or blocked?",
      "expected_output": "A roadmap with any delivering/blocked batch entry wins the ranking outright over every other candidate.",
      "files": ["skills/roadmap-continuing/references/liveness-ranking.md"],
      "assertions": [
        { "type": "convention", "check": "delivering/blocked-wins rule documented as step 2 of the algorithm", "observed": "present", "result": "pass" }
      ]
    },
    {
      "id": 5, "scope": "behavior", "set": "train",
      "prompt": "Does the skill fall back to newest Log date when no candidate is delivering/blocked?",
      "expected_output": "Among remaining candidates, the most recent ## Log entry timestamp wins.",
      "files": ["skills/roadmap-continuing/references/liveness-ranking.md"],
      "assertions": [
        { "type": "convention", "check": "newest-Log-date fallback documented as step 3", "observed": "present", "result": "pass" }
      ]
    },
    {
      "id": 6, "scope": "behavior", "set": "train",
      "prompt": "Does the skill present the roadmap state before asking?",
      "expected_output": "The '## Present state' section (Goal, current batch, newest Log line) runs before the '## Ask once' section.",
      "files": ["skills/roadmap-continuing/SKILL.md"],
      "assertions": [
        { "type": "convention", "check": "Present state precedes Ask once in document order", "observed": "present", "result": "pass" }
      ]
    },
    {
      "id": 7, "scope": "behavior", "set": "validation",
      "prompt": "Does the skill ask 'auto or guided?' exactly once?",
      "expected_output": "Exactly one ask, after presenting state; never re-asked.",
      "files": ["skills/roadmap-continuing/SKILL.md"],
      "assertions": [
        { "type": "convention", "check": "the literal phrase 'auto or guided' appears on exactly one line of SKILL.md", "observed": "one occurrence", "result": "pass" }
      ]
    },
    {
      "id": 8, "scope": "behavior", "set": "validation",
      "prompt": "Does the skill invent a new roadmap or INDEX status field, or add a new script?",
      "expected_output": "No. Liveness is computed at read time from existing files; INDEX.md stays the sole status writer; the enumeration/ranking is prose, not a helper script.",
      "files": ["skills/roadmap-continuing/SKILL.md", "skills/roadmap-continuing/references/liveness-ranking.md"],
      "assertions": [
        { "type": "convention", "check": "no new field or script introduced; 'No new script' section present", "observed": "present", "result": "pass" }
      ]
    }
  ]
}