Files
ai-proj-helper/skills-dev/agent-browser-plugin/skills/evals/evals.json
T
johnQ 7b221cc767
skill-gate / gate (push) Waiting to run
docs(skill): 覆盖率阶段 2 完成 —— 全量 evals 与四段式文档清零
- 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)
2026-11-01 05:19:28 +08:00

28 lines
827 B
JSON

{
"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": []
}
]
}