{
  "skill_name": "dashboard-spec",
  "evals": [
    {
      "id": 1,
      "prompt": "Acme's VP of sales wants an exec dashboard for the Tuesday pipeline review, where she decides which deals need executive help and whether the quarter's forecast needs changing. Requested: total revenue all-time, pipeline by stage, win rate, average deal size, deals by rep, a leaderboard of calls made, website visitors, forecast vs quota, deals slipping past close date, and a map of customers. Defined metrics: `pipeline_value_usd` and `quarter_forecast_usd` (quota is $12M for the quarter). Data is in Salesforce, synced to BigQuery every 6 hours.",
      "assertions": [
        "Opens with a one-sentence decision statement naming the VP of sales, the Tuesday cadence, and both decisions (exec help on deals, forecast change)",
        "Lists at most seven questions in priority order, each with the action a bad answer triggers",
        "Gives each question one chart with a chart type and a one-line reason, and no chart without a question",
        "References pipeline_value_usd and quarter_forecast_usd by name and flags win rate, deal size and slipping deals as undefined build blockers rather than inventing definitions",
        "Shows forecast against the $12M quota as a comparison, not a bare number",
        "Cuts total revenue all-time, the calls leaderboard, website visitors and the map, each with a reason",
        "Sets a refresh and freshness SLA consistent with a weekly decision and the 6-hour sync, with stale-data behaviour",
        "Does not invent targets, owners or metrics not given in the prompt; assumptions are tagged"
      ]
    }
  ]
}