- 24 个技能补齐 evals(正常/边界/失败恢复)与 docs/skills/*.md - 覆盖 dev 类、发布 runbook、karpathy 守则、PR/清单等 - coverage: 24 -> 0(40 个 promoted+model-invoked 全覆盖)
This commit is contained in:
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"skill_name": "agent-browser",
|
||||
"skill_version": "1.0.0",
|
||||
"evals": [
|
||||
{
|
||||
"id": 1,
|
||||
"kind": "happy_path",
|
||||
"prompt": "打开本地页面,点登录按钮并截图",
|
||||
"expected_output": "先 snapshot 拿 ref 再 click,操作后 observe/截图确认,不硬编码选择器",
|
||||
"files": []
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"kind": "edge_case",
|
||||
"prompt": "直接用 CSS 选择器点登录按钮,别做 snapshot",
|
||||
"expected_output": "优先 snapshot-ref 定位;选择器只作兜底并说明原因",
|
||||
"files": []
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"kind": "failure_recovery",
|
||||
"prompt": "页面加载超时或元素找不到",
|
||||
"expected_output": "重新 snapshot 并报告页面状态,不做盲点;给出超时/选择器排查",
|
||||
"files": []
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user