update by wensicheng on 0629

skills/requirements-analysis/evals/evals.json

@@ -2,25 +2,19 @@
   "skill_name": "requirements-analysis",
   "evals": [
     {
-      "id": 1,
-      "name": "vague-no-schema",
-      "prompt": "帮我统计下近30天新用户转化率",
-      "expected_output": "应主动索要相关表/schema/字段说明，并对'近30天'、'新用户'、'转化'这三个词分别提出多选式澄清问题。不应直接生成 SQL 或假设口径。",
-      "files": []
+      "id": "ambiguous-conversion-rate",
+      "prompt": "帮我看下最近一个月新用户转化率",
+      "expected_behavior": "必须追问最近一个月的时间边界、新用户定义、转化动作、分子分母、去重键和候选表字段；不能直接写 SQL。"
     },
     {
-      "id": 2,
-      "name": "schema-with-ambiguity",
-      "prompt": "统计上周每个渠道的支付成功订单数和支付金额。表结构如下：\n\norder_info(\n    order_id bigint,\n    user_id bigint,\n    channel_id int,\n    create_time timestamp,\n    pay_time timestamp,\n    status int,  -- 1待支付 2已支付 3已发货 4已完成 5已退款 6部分退款\n    amount decimal(18,2),  -- 应付金额\n    paid_amount decimal(18,2)  -- 实付金额\n)\n\nchannel_dim(\n    channel_id int,\n    channel_name varchar\n)",
-      "expected_output": "应识别出'支付成功'状态码歧义（2/3/4/6 是否都算）、'支付金额'是 amount 还是 paid_amount、'上周'是自然周还是滚动 7 天、退款订单是否计入。应提议 left join channel_dim。不应直接生成 SQL。",
-      "files": []
+      "id": "orders-with-schema",
+      "prompt": "统计上周各渠道支付成功订单数和金额，并给出 order_info/channel_dim schema",
+      "expected_behavior": "必须确认上周口径、支付成功状态、金额字段、退款是否计入、join 类型和输出粒度。"
     },
     {
-      "id": 3,
-      "name": "multi-table-loan",
-      "prompt": "我要算下贷款产品的首贷转化漏斗，从注册到首次申请到首次放款的转化率，按月看趋势。表：\n\nuser_register(user_id bigint, register_time timestamp, channel varchar)\nloan_apply(apply_id bigint, user_id bigint, apply_time timestamp, product_id int, apply_amount decimal)\nloan_disburse(disburse_id bigint, apply_id bigint, disburse_time timestamp, disburse_amount decimal, status int)\nproduct_dim(product_id int, product_name varchar, product_type varchar)",
-      "expected_output": "应识别多表 join 关系（user → apply 按 user_id, apply → disburse 按 apply_id），追问首贷定义（按用户首次还是按产品首次）、放款 status 含义、'按月看'是注册月还是事件发生月、是否限定产品类型、漏斗分母是否包含没注册成功的用户。",
-      "files": []
+      "id": "loan-funnel",
+      "prompt": "做注册到申请到放款的贷款漏斗，按月看",
+      "expected_behavior": "必须确认月份归属、首贷定义、放款成功状态、漏斗分母、用户去重和 user/apply/disburse 关联关系。"
     }
   ]
-}
+}