- 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": "executing-plans",
|
||||
"skill_version": "1.0.0",
|
||||
"evals": [
|
||||
{
|
||||
"id": 1,
|
||||
"kind": "happy_path",
|
||||
"prompt": "按这份计划开始执行",
|
||||
"expected_output": "分步执行、每步检查点、偏差报告",
|
||||
"files": []
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"kind": "edge_case",
|
||||
"prompt": "计划和现状不一致,直接按计划硬推",
|
||||
"expected_output": "停下确认:报告差异并等决策",
|
||||
"files": []
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"kind": "failure_recovery",
|
||||
"prompt": "执行到某步失败",
|
||||
"expected_output": "阻塞并报告(失败步骤+证据+选项),不硬推",
|
||||
"files": []
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user