Files
MetaSkill/skills/le-app-design/reports/trigger-eval.json
T

221 lines
5.3 KiB
JSON

{
"skill": "le-app-design",
"date": "2026-11-07",
"threshold": 0.3,
"prediction_mode": "coverage_fallback",
"note": "词面冒烟测试;行为结论需真实对话实测(live_turns 字段手工补记)",
"cases": [
{
"text": "帮我设计一个习惯打卡 App,要能看的高保真原型",
"family": "full_design_cn",
"bucket": "should_trigger",
"coverage": 0.5,
"coverage_hits": [
"app",
"保真",
"原型",
"我设",
"真原",
"计一",
"设计",
"高保"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": true,
"expected_trigger": true,
"verdict": "pass"
},
{
"text": "把这个产品想法做成可交互的 UI 原型,从设计到成品",
"family": "full_design_cn",
"bucket": "should_trigger",
"coverage": 0.444,
"coverage_hits": [
"ui",
"个产",
"交互",
"产品",
"原型",
"可交",
"想法",
"设计"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": true,
"expected_trigger": true,
"verdict": "pass"
},
{
"text": "design an app for my recipe startup, high-fidelity prototype",
"family": "full_design_en",
"bucket": "should_trigger",
"coverage": 0.3,
"coverage_hits": [
"an",
"app",
"design"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": true,
"expected_trigger": true,
"verdict": "pass"
},
{
"text": "给我的工具类产品做一轮完整的设计:规范、视觉、原型加审查",
"family": "full_pipeline",
"bucket": "should_trigger",
"coverage": 0.476,
"coverage_hits": [
"产品",
"做一",
"原型",
"品做",
"完整",
"审查",
"整的",
"规范",
"视觉",
"设计"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": true,
"expected_trigger": true,
"verdict": "pass"
},
{
"text": "我要做个妈妈育儿 App,帮我把首页和详情页设计出来",
"family": "app_screens",
"bucket": "should_trigger",
"coverage": 0.5,
"coverage_hits": [
"app",
"和详",
"情页",
"把首",
"计出",
"设计",
"详情",
"页和",
"首页"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": true,
"expected_trigger": true,
"verdict": "pass"
},
{
"text": "用 le-app-design 把这个 idea 变成原型",
"family": "explicit_name",
"bucket": "should_trigger",
"coverage": 0.444,
"coverage_hits": [
"app",
"design",
"le",
"原型"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": true,
"expected_trigger": true,
"verdict": "pass"
},
{
"text": "用 impeccable 审查一下这个页面",
"family": "single_upstream_direct",
"bucket": "should_not_trigger",
"coverage": 0.429,
"coverage_hits": [
"impeccable",
"审查",
"页面"
],
"families_hit": [],
"negative_hit": true,
"predicted_trigger": false,
"expected_trigger": false,
"verdict": "pass"
},
{
"text": "ui-ux-pro-max 帮我查个配色",
"family": "single_upstream_direct",
"bucket": "should_not_trigger",
"coverage": 0.5,
"coverage_hits": [
"max",
"pro",
"ui",
"ux"
],
"families_hit": [],
"negative_hit": true,
"predicted_trigger": false,
"expected_trigger": false,
"verdict": "pass"
},
{
"text": "帮我写一篇公众号文章",
"family": "other_le_skill",
"bucket": "should_not_trigger",
"coverage": 0.0,
"coverage_hits": [],
"families_hit": [],
"negative_hit": true,
"predicted_trigger": false,
"expected_trigger": false,
"verdict": "pass"
},
{
"text": "给我生成一张 App 封面图",
"family": "image_only",
"bucket": "should_not_trigger",
"coverage": 0.25,
"coverage_hits": [
"app",
"生成"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": false,
"expected_trigger": false,
"verdict": "pass"
},
{
"text": "这个按钮的点击事件没反应,帮我修一下",
"family": "pure_dev",
"bucket": "should_not_trigger",
"coverage": 0.0,
"coverage_hits": [],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": false,
"expected_trigger": false,
"verdict": "pass"
},
{
"text": "把这个页面布局调好看一点",
"family": "local_tweak",
"bucket": "near_neighbor",
"coverage": 0.1,
"coverage_hits": [
"页面"
],
"families_hit": [],
"negative_hit": false,
"predicted_trigger": false,
"expected_trigger": null,
"verdict": "boundary"
}
],
"summary": {
"scored": 11,
"mismatch": 0,
"pass_rate": 1.0
}
}