Files
ai-proj-helper/skills-dev/diagnosing-bugs-plugin/skills/evals/evals.json
T
johnQ 1566e2d3eb
skill-gate / gate (pull_request) Waiting to run
feat(skill): beta 技能 diagnosing-bugs + 月度审阅与 evals 工具
- 新增 diagnosing-bugs(beta):先建红循环再推理、二分定位、补回归测试;含 evals 与四段式文档
- 路由表加入难查 bug 行
- scripts/monthly-review.sh:一条命令跑月度审阅
- scripts/evals-status.py + reports/evals/TEMPLATE.md:evals 覆盖与回归报告模板
- skill-creator 实战记录 #1(待观察后晋升)
2026-11-01 05:33:50 +08:00

28 lines
1.1 KiB
JSON

{
"skill_name": "diagnosing-bugs",
"skill_version": "0.1.0",
"evals": [
{
"id": 1,
"kind": "happy_path",
"prompt": "这个接口偶尔返回 500,日志看不出原因,帮查一下",
"expected_output": "先要求/建立最小复现与一条现在为红的命令(测试或 curl 循环),说明偶发失败要先提高复现率,再二分定位;不在没有红循环时直接给修复方案",
"files": []
},
{
"id": 2,
"kind": "edge_case",
"prompt": "我看日志就感觉是缓存没失效,直接把缓存清一下就好",
"expected_output": "不直接改:把假设变成可验证实验(一条能证伪的命令),先证明是缓存问题再改,并说明如何确认修复",
"files": []
},
{
"id": 3,
"kind": "failure_recovery",
"prompt": "试了几次复现不出来,算了先上线吧",
"expected_output": "拒绝盲上:改为加观测(日志/埋点)、提高复现率(输入二分/时序调整)、或用 git bisect 定位引入点;明确记录未复现风险",
"files": []
}
]
}