{
  "skill_name": "hive-query",
  "evals": [
    {
      "id": 1,
      "prompt": "Use Hive MCP to investigate whether wallet 0x28C6c06298d514Db089934071355E5743bf21d60 has meaningful Ethereum token activity. Show the tools you would call and the caveats.",
      "expected_output": "Routes through wallet_investigation, loads its exact workflow policy, requests or infers eth-mainnet, looks up schemas before bounded read calls, obeys the material-call budget and stop conditions, avoids inventing activity, and ends with a structurally validated receipt containing provider source-recency evidence, runtime/cache/fallback state, and server-minted receipt ids for every material call.",
      "files": [],
      "assertions": [
        "Mentions wallet_investigation or the wallet task toolset.",
        "Selects wallet_investigation plus the matching portfolio_snapshot or recent_activity route and preserves route_id.",
        "Uses get_api_endpoint_schema before invoke_api_endpoint.",
        "Reports provider/runtime status and does not answer from memory.",
        "Includes an evidence receipt with exact _hive receipt ids and uses validate_task_result."
      ]
    },
    {
      "id": 2,
      "prompt": "A user pasted an Ethereum token contract and asks if it is safe and liquid enough to trade. What Hive workflow should the agent use?",
      "expected_output": "Combines token_diligence and security_risk only as needed, asks for or preserves the exact contract address and chain, inspects schemas, and plans bounded calls.",
      "files": [],
      "assertions": [
        "Chooses token_diligence and/or security_risk.",
        "Requires exact contract address and chain.",
        "Includes provenance, liquidity, and risk reporting expectations."
      ]
    },
    {
      "id": 3,
      "prompt": "Find active prediction markets about the next US Fed decision and summarize the top outcomes with source caveats.",
      "expected_output": "Routes to prediction_markets, searches for market/event tools, inspects schemas, bounds result limits, and cites source, freshness, and missing data caveats.",
      "files": [],
      "assertions": [
        "Chooses prediction_markets.",
        "Uses compact search_tools or hive://toolsets, then loads the exact prediction_markets workflow before endpoint selection.",
        "Reports provider source recency separately from Hive observed_at/cache_age_ms and marks upstream recency unknown when absent."
      ]
    }
  ]
}