wuyang/zk-data-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: add skill evaluation workbench design

Browse Source
This commit is contained in:
wuyang6
2026-07-23 16:49:53 +08:00
parent 97e1e1dd48
commit 0e4f5041f1
5 changed files with 733 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/assets/planning-data-driven-loop-v1.svg
+148
View File
@@ -0,0 +1,148 @@
<svg width="1600" height="900" viewBox="0 0 1600 900" xmlns="http://www.w3.org/2000/svg">
<defs>
<marker id="arrow" markerWidth="12" markerHeight="12" refX="10" refY="6" orient="auto">
<path d="M2,2 L10,6 L2,10 Z" fill="#64748b"/>
</marker>
<marker id="arrowBlue" markerWidth="12" markerHeight="12" refX="10" refY="6" orient="auto">
<path d="M2,2 L10,6 L2,10 Z" fill="#2563eb"/>
</marker>
<filter id="softShadow" x="-10%" y="-10%" width="120%" height="130%">
<feDropShadow dx="0" dy="8" stdDeviation="10" flood-color="#0f172a" flood-opacity="0.10"/>
</filter>
<style>
.title { font: 700 38px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.subtitle { font: 400 20px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #475569; }
.sectionTitle { font: 700 22px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.stepNo { font: 700 17px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #64748b; }
.stepTitle { font: 700 19px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.stepText { font: 400 14px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #475569; }
.badge { font: 700 13px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #9a3412; }
.baseTitle { font: 700 24px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.baseMain { font: 700 28px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #1e293b; }
.baseSub { font: 400 18px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #475569; }
.chip { font: 600 15px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #334155; }
.loopLabel { font: 600 17px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #2563eb; }
</style>
</defs>
<rect width="1600" height="900" fill="#f8fafc"/>
<text x="800" y="72" text-anchor="middle" class="title">planning 模型数据驱动迭代链路</text>
<text x="800" y="108" text-anchor="middle" class="subtitle">从问题发现到模型改进：数据开发 + AutoResearch + Agent 平台底座的全流程提效</text>
<!-- Main entry: problem discovery -->
<g filter="url(#softShadow)">
<rect x="68" y="220" width="190" height="130" rx="18" fill="#ffffff" stroke="#dbeafe" stroke-width="2"/>
<text x="95" y="253" class="stepNo">1</text>
<text x="163" y="283" text-anchor="middle" class="stepTitle">问题发现</text>
<text x="163" y="314" text-anchor="middle" class="stepText">线上 badcase</text>
<text x="163" y="337" text-anchor="middle" class="stepText">评测错误 / 指标异常</text>
</g>
<!-- Data development module -->
<g filter="url(#softShadow)">
<rect x="300" y="170" width="690" height="230" rx="24" fill="#eef6ff" stroke="#bfdbfe" stroke-width="2"/>
<text x="645" y="205" text-anchor="middle" class="sectionTitle">数据开发提效</text>
<text x="645" y="232" text-anchor="middle" class="stepText">把问题转成可训练、可评测的数据资产</text>
</g>
<!-- AutoResearch module -->
<g filter="url(#softShadow)">
<rect x="1040" y="170" width="455" height="230" rx="24" fill="#f5f3ff" stroke="#ddd6fe" stroke-width="2"/>
<text x="1267" y="205" text-anchor="middle" class="sectionTitle">AutoResearch</text>
<text x="1267" y="232" text-anchor="middle" class="stepText">planning 模型迭代与结构分析</text>
</g>
<!-- Step boxes: data development -->
<g>
<rect x="330" y="265" width="140" height="95" rx="16" fill="#ffffff" stroke="#bfdbfe" stroke-width="1.5"/>
<text x="350" y="292" class="stepNo">2</text>
<text x="400" y="316" text-anchor="middle" class="stepTitle">线上数据挖掘</text>
<text x="400" y="342" text-anchor="middle" class="stepText">rid / session</text>
<text x="400" y="362" text-anchor="middle" class="stepText">prompt / output</text>
</g>
<g>
<rect x="500" y="265" width="150" height="95" rx="16" fill="#fff7ed" stroke="#fed7aa" stroke-width="1.8"/>
<text x="520" y="292" class="stepNo">3</text>
<text x="575" y="316" text-anchor="middle" class="stepTitle">问题分析</text>
<text x="575" y="342" text-anchor="middle" class="stepText">归因 / 标签边界</text>
<rect x="536" y="352" width="78" height="24" rx="12" fill="#ffedd5" stroke="#fdba74"/>
<text x="575" y="369" text-anchor="middle" class="badge">人工 Review</text>
</g>
<g>
<rect x="680" y="265" width="140" height="95" rx="16" fill="#ffffff" stroke="#bfdbfe" stroke-width="1.5"/>
<text x="700" y="292" class="stepNo">4</text>
<text x="750" y="316" text-anchor="middle" class="stepTitle">数据构造</text>
<text x="750" y="342" text-anchor="middle" class="stepText">训练样本</text>
<text x="750" y="362" text-anchor="middle" class="stepText">评测样本 / 边界样例</text>
</g>
<g>
<rect x="850" y="265" width="115" height="95" rx="16" fill="#ffffff" stroke="#bfdbfe" stroke-width="1.5"/>
<text x="868" y="292" class="stepNo">5</text>
<text x="907" y="316" text-anchor="middle" class="stepTitle">格式转换</text>
<text x="907" y="342" text-anchor="middle" class="stepText">CSV / JSONL</text>
<text x="907" y="362" text-anchor="middle" class="stepText">eval set</text>
</g>
<!-- Step boxes: autoresearch -->
<g>
<rect x="1072" y="265" width="155" height="95" rx="16" fill="#ffffff" stroke="#ddd6fe" stroke-width="1.5"/>
<text x="1092" y="292" class="stepNo">6</text>
<text x="1149" y="316" text-anchor="middle" class="stepTitle">planning 模型迭代</text>
<text x="1149" y="342" text-anchor="middle" class="stepText">训练 / 评测</text>
<text x="1149" y="362" text-anchor="middle" class="stepText">配置实验</text>
</g>
<g>
<rect x="1262" y="265" width="200" height="95" rx="16" fill="#fff7ed" stroke="#fed7aa" stroke-width="1.8"/>
<text x="1282" y="292" class="stepNo">7</text>
<text x="1362" y="316" text-anchor="middle" class="stepTitle">结构分析 / 结果分析</text>
<text x="1362" y="342" text-anchor="middle" class="stepText">指标拆解 / 回归验证</text>
<rect x="1323" y="352" width="78" height="24" rx="12" fill="#ffedd5" stroke="#fdba74"/>
<text x="1362" y="369" text-anchor="middle" class="badge">人工 Review</text>
</g>
<!-- Straight arrows -->
<path d="M258 285 L318 285" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M470 312 L492 312" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M650 312 L672 312" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M820 312 L842 312" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M965 312 L1064 312" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M1227 312 L1254 312" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<!-- Feedback loop -->
<path d="M1362 402 C1362 500 1070 505 820 505 C465 505 163 485 163 365" stroke="#2563eb" stroke-width="3" stroke-dasharray="8 8" fill="none" marker-end="url(#arrowBlue)"/>
<text x="760" y="486" text-anchor="middle" class="loopLabel">新 badcase / 新边界 / 新样本 / 新策略回流</text>
<!-- Platform base -->
<g filter="url(#softShadow)">
<rect x="90" y="570" width="1410" height="210" rx="28" fill="#ffffff" stroke="#cbd5e1" stroke-width="2"/>
<text x="795" y="615" text-anchor="middle" class="baseTitle">ZK Data Agent 平台底座</text>
<text x="795" y="663" text-anchor="middle" class="baseMain">Agent Loop + Skill + 工具链 + 记忆 + Jupyter 工作区</text>
<text x="795" y="699" text-anchor="middle" class="baseSub">通过 Agent Loop 调度 Skill 和工具，连接线上数据、执行环境与产物沉淀</text>
<g>
<rect x="205" y="725" width="140" height="34" rx="17" fill="#f1f5f9"/>
<text x="275" y="748" text-anchor="middle" class="chip">线上日志工具</text>
<rect x="375" y="725" width="120" height="34" rx="17" fill="#f1f5f9"/>
<text x="435" y="748" text-anchor="middle" class="chip">标签知识</text>
<rect x="525" y="725" width="150" height="34" rx="17" fill="#f1f5f9"/>
<text x="600" y="748" text-anchor="middle" class="chip">数据格式转换</text>
<rect x="705" y="725" width="120" height="34" rx="17" fill="#f1f5f9"/>
<text x="765" y="748" text-anchor="middle" class="chip">会话沉淀</text>
<rect x="855" y="725" width="130" height="34" rx="17" fill="#f1f5f9"/>
<text x="920" y="748" text-anchor="middle" class="chip">运行态观测</text>
<rect x="1015" y="725" width="155" height="34" rx="17" fill="#f1f5f9"/>
<text x="1092" y="748" text-anchor="middle" class="chip">账号 / 工作区隔离</text>
<rect x="1200" y="725" width="160" height="34" rx="17" fill="#f1f5f9"/>
<text x="1280" y="748" text-anchor="middle" class="chip">训练评测工具链</text>
</g>
</g>
<!-- Thin connector from business flow to base -->
<path d="M795 526 L795 565" stroke="#94a3b8" stroke-width="2" stroke-dasharray="5 6"/>
<text x="825" y="548" class="stepText">平台能力支撑全链路</text>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 9.4 KiB

docs/assets/planning-data-driven-loop-v1.svg.png
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 380 KiB

docs/assets/planning-data-driven-loop-v2.svg
+133
View File
@@ -0,0 +1,133 @@
<svg width="1600" height="900" viewBox="0 0 1600 900" xmlns="http://www.w3.org/2000/svg">
<defs>
<marker id="arrow" markerWidth="12" markerHeight="12" refX="10" refY="6" orient="auto">
<path d="M2,2 L10,6 L2,10 Z" fill="#64748b"/>
</marker>
<marker id="arrowBlue" markerWidth="12" markerHeight="12" refX="10" refY="6" orient="auto">
<path d="M2,2 L10,6 L2,10 Z" fill="#2563eb"/>
</marker>
<marker id="arrowPurple" markerWidth="12" markerHeight="12" refX="10" refY="6" orient="auto">
<path d="M2,2 L10,6 L2,10 Z" fill="#7c3aed"/>
</marker>
<filter id="softShadow" x="-10%" y="-10%" width="120%" height="130%">
<feDropShadow dx="0" dy="8" stdDeviation="10" flood-color="#0f172a" flood-opacity="0.10"/>
</filter>
<style>
.title { font: 700 38px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.subtitle { font: 400 20px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #475569; }
.sectionTitle { font: 700 22px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.sectionSub { font: 400 14px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #64748b; }
.stepNo { font: 700 17px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #64748b; }
.stepTitle { font: 700 19px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #0f172a; }
.stepText { font: 400 14px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #475569; }
.badge { font: 700 13px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #9a3412; }
.loopLabel { font: 600 17px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #2563eb; }
.iterLabel { font: 700 16px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #6d28d9; }
.base { font: 600 18px -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif; fill: #475569; }
</style>
</defs>
<rect width="1600" height="900" fill="#f8fafc"/>
<text x="800" y="76" text-anchor="middle" class="title">planning 模型数据驱动迭代链路</text>
<text x="800" y="112" text-anchor="middle" class="subtitle">从问题发现到模型改进：数据开发 + AutoResearch 的全流程提效</text>
<!-- Step 1 -->
<g filter="url(#softShadow)">
<rect x="70" y="265" width="185" height="120" rx="18" fill="#ffffff" stroke="#dbeafe" stroke-width="2"/>
<text x="94" y="297" class="stepNo">1</text>
<text x="162" y="323" text-anchor="middle" class="stepTitle">问题发现</text>
<text x="162" y="351" text-anchor="middle" class="stepText">线上 badcase</text>
<text x="162" y="373" text-anchor="middle" class="stepText">评测错误 / 指标异常</text>
</g>
<!-- Data development module -->
<g filter="url(#softShadow)">
<rect x="300" y="190" width="640" height="250" rx="24" fill="#eef6ff" stroke="#bfdbfe" stroke-width="2"/>
<text x="620" y="226" text-anchor="middle" class="sectionTitle">数据开发提效</text>
<text x="620" y="252" text-anchor="middle" class="sectionSub">把问题转成可训练、可评测的数据资产</text>
</g>
<!-- Data development steps -->
<g>
<rect x="335" y="300" width="150" height="105" rx="16" fill="#ffffff" stroke="#bfdbfe" stroke-width="1.5"/>
<text x="358" y="329" class="stepNo">2</text>
<text x="410" y="352" text-anchor="middle" class="stepTitle">线上数据挖掘</text>
<text x="410" y="379" text-anchor="middle" class="stepText">rid / session</text>
<text x="410" y="399" text-anchor="middle" class="stepText">prompt / output</text>
</g>
<g>
<rect x="535" y="300" width="155" height="105" rx="16" fill="#fff7ed" stroke="#fed7aa" stroke-width="1.8"/>
<text x="558" y="329" class="stepNo">3</text>
<text x="612" y="352" text-anchor="middle" class="stepTitle">问题分析</text>
<text x="612" y="379" text-anchor="middle" class="stepText">归因 / 标签边界</text>
<rect x="573" y="389" width="78" height="24" rx="12" fill="#ffedd5" stroke="#fdba74"/>
<text x="612" y="406" text-anchor="middle" class="badge">人工 Review</text>
</g>
<g>
<rect x="740" y="300" width="165" height="105" rx="16" fill="#ffffff" stroke="#bfdbfe" stroke-width="1.5"/>
<text x="763" y="329" class="stepNo">4</text>
<text x="822" y="352" text-anchor="middle" class="stepTitle">数据构造</text>
<text x="822" y="379" text-anchor="middle" class="stepText">样本生成 / 格式转换</text>
<text x="822" y="399" text-anchor="middle" class="stepText">训练集 / 评测集</text>
</g>
<!-- AutoResearch module -->
<g filter="url(#softShadow)">
<rect x="990" y="190" width="450" height="250" rx="24" fill="#f5f3ff" stroke="#ddd6fe" stroke-width="2"/>
<text x="1215" y="226" text-anchor="middle" class="sectionTitle">AutoResearch</text>
<text x="1215" y="252" text-anchor="middle" class="sectionSub">planning 模型迭代与结构分析</text>
</g>
<!-- AutoResearch steps -->
<g>
<rect x="1028" y="300" width="165" height="105" rx="16" fill="#ffffff" stroke="#ddd6fe" stroke-width="1.5"/>
<text x="1051" y="329" class="stepNo">5</text>
<text x="1110" y="352" text-anchor="middle" class="stepTitle">planning 模型迭代</text>
<text x="1110" y="379" text-anchor="middle" class="stepText">训练 / 评测</text>
<text x="1110" y="399" text-anchor="middle" class="stepText">配置实验</text>
</g>
<g>
<rect x="1248" y="300" width="160" height="105" rx="16" fill="#fff7ed" stroke="#fed7aa" stroke-width="1.8"/>
<text x="1271" y="329" class="stepNo">6</text>
<text x="1328" y="352" text-anchor="middle" class="stepTitle">结构分析 / 结果分析</text>
<text x="1328" y="379" text-anchor="middle" class="stepText">指标拆解 / 回归验证</text>
<rect x="1289" y="389" width="78" height="24" rx="12" fill="#ffedd5" stroke="#fdba74"/>
<text x="1328" y="406" text-anchor="middle" class="badge">人工 Review</text>
</g>
<!-- Step 7 online -->
<g filter="url(#softShadow)">
<rect x="1128" y="520" width="175" height="100" rx="18" fill="#ffffff" stroke="#cbd5e1" stroke-width="2"/>
<text x="1152" y="550" class="stepNo">7</text>
<text x="1215" y="576" text-anchor="middle" class="stepTitle">模型上线</text>
<text x="1215" y="604" text-anchor="middle" class="stepText">发布 / 观察 / 回流</text>
</g>
<!-- Main arrows -->
<path d="M255 325 L326 325" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M485 352 L526 352" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M690 352 L731 352" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<path d="M905 352 L1019 352" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<!-- Iteration loop between 5 and 6 -->
<path d="M1195 325 C1222 292 1250 292 1275 319" stroke="#7c3aed" stroke-width="3" fill="none" marker-end="url(#arrowPurple)"/>
<path d="M1276 385 C1248 424 1218 424 1194 391" stroke="#7c3aed" stroke-width="3" fill="none" marker-end="url(#arrowPurple)"/>
<text x="1218" y="286" text-anchor="middle" class="iterLabel">循环迭代</text>
<!-- From 6 to 7 -->
<path d="M1328 405 C1328 480 1260 498 1225 514" stroke="#64748b" stroke-width="3" fill="none" marker-end="url(#arrow)"/>
<!-- Feedback loop from 7 to 1 -->
<path d="M1128 570 C920 690 520 690 270 585 C175 545 142 470 154 395" stroke="#2563eb" stroke-width="3" stroke-dasharray="8 8" fill="none" marker-end="url(#arrowBlue)"/>
<text x="650" y="660" text-anchor="middle" class="loopLabel">新 badcase / 新边界 / 新样本 / 新策略回流</text>
<!-- Light platform support bar -->
<g>
<rect x="140" y="752" width="1320" height="58" rx="18" fill="#f1f5f9" stroke="#e2e8f0" stroke-width="1"/>
<text x="800" y="788" text-anchor="middle" class="base">ZK Data Agent 支撑：通过 Agent Loop 调度 Skill 和工具，连接线上数据、执行环境与产物沉淀</text>
</g>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 8.2 KiB