[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GK47VMFRKJ09TG78V7C74D":3,"skill-same:01M6GK47VMFRKJ09TG78V7C74D":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":13,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6GK47VMFRKJ09TG78V7C74D","调度并行代理",null,"当面临 2 个以上彼此独立、没有共享状态或顺序依赖的任务时使用","lihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit","lihah111222333-cloud","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F254297992?v=4","01M6GJZ7ZK31PVRBS5XQWS56ET","01M6GJZ84Q0ANFYMPVK56PYSNW",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002F调度并行代理\u002FSKILL.md",[],[5,18,19,20,21],"orchestration","parallel","agent-orchestration","并行代理调度","2026-11-10 10:12:30",false,"---\nname: 调度并行代理\ndescription: 当面临 2 个以上彼此独立、没有共享状态或顺序依赖的任务时使用\naliases: [\"@调度并行代理\", \"@并行代理调度\", \"@parallel-agent-orchestration\"]\n---\n\n# 调度并行代理\n\n## 概览\n\n你会把任务委派给拥有隔离上下文的专门代理。通过精确编写它们的指令和上下文，你可以确保它们保持聚焦并完成任务。它们不应该继承你的会话上下文或历史；你要只构造它们需要的内容。这也能保留你自己的上下文，用于协调工作。\n\n当你有多个无关失败（不同测试文件、不同子系统、不同 bug）时，逐个调查会浪费时间。每个调查都独立，可以并行进行。\n\n**核心原则：** 每个独立问题域派发一个代理。让它们并发工作。\n\n**super-agent-v3 编排选择：** 并行代理不强制绑定 mcp-orch。优先使用当前平台可用的原生多代理能力；只有需要持久 DAG、重试、租约、cron\u002Fwakeup 或结构化交接记录时，才可选使用 `task_create_dag`、`task_start_dag`、`task_dispatch_node`、`task_update_node`。缺少 mcp-go-agent-orchestration 工具不是阻断条件；继续使用可用的子代理能力，或在不适合派发时改为单代理只读分析并说明观测限制。\n\n## 何时使用\n\n```dot\ndigraph when_to_use {\n    \"Multiple failures?\" [shape=diamond];\n    \"Are they independent?\" [shape=diamond];\n    \"Single agent investigates all\" [shape=box];\n    \"One agent per problem domain\" [shape=box];\n    \"Can they work in parallel?\" [shape=diamond];\n    \"Sequential agents\" [shape=box];\n    \"Parallel dispatch\" [shape=box];\n\n    \"Multiple failures?\" -> \"Are they independent?\" [label=\"yes\"];\n    \"Are they independent?\" -> \"Single agent investigates all\" [label=\"no - related\"];\n    \"Are they independent?\" -> \"Can they work in parallel?\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Parallel dispatch\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Sequential agents\" [label=\"no - shared state\"];\n}\n```\n\n**适用场景：**\n- 3 个以上测试文件失败，且根因不同\n- 多个子系统独立损坏\n- 每个问题不需要其他问题的上下文就能理解\n- 调查之间没有共享状态\n\n**不适用场景：**\n- 失败彼此相关（修复一个可能修复其他）\n- 需要理解完整系统状态\n- 代理会相互干扰\n\n## 模式\n\n### 1. 识别独立域\n\n按损坏内容分组失败：\n- 文件 A 测试：工具批准流程\n- 文件 B 测试：批量完成行为\n- 文件 C 测试：中止功能\n\n每个域都是独立的：修复工具批准不会影响中止测试。\n\n### 2. 创建聚焦的代理任务\n\n每个代理得到：\n- **具体范围：** 一个测试文件或子系统\n- **明确目标：** 让这些测试通过\n- **约束：** 不要修改其他代码\n- **预期输出：** 总结发现和修复内容\n\n### 3. 并行派发\n\n平台原生多代理可直接派发。若本轮明确选择 mcp-orch 记录持久编排状态，可按下面方式建 DAG：\n\n```typescript\ntask_create_dag({\n  dag_key: \"fix-independent-test-failures\",\n  nodes: [\n    { node_key: \"agent-tool-abort\", assigned_to: \"worker\", depends_on: [] },\n    { node_key: \"batch-completion\", assigned_to: \"worker\", depends_on: [] },\n    { node_key: \"tool-approval-race\", assigned_to: \"worker\", depends_on: [] }\n  ]\n})\ntask_start_dag(\"fix-independent-test-failures\")\ntask_dispatch_node(\"agent-tool-abort\", run_id, assigned_to)\ntask_dispatch_node(\"batch-completion\", run_id, assigned_to)\ntask_dispatch_node(\"tool-approval-race\", run_id, assigned_to)\n```\n\n如果使用平台原生多代理，保留每个子代理的范围、返回摘要、文件改动和验证结果；不需要伪造 DAG\u002Fnode 证据。\n\n### 4. 审阅并集成\n\n代理返回后：\n- 阅读每份总结\n- 验证修复之间没有冲突\n- 运行完整测试套件\n- 集成所有变更\n\n## 代理提示词结构\n\n好的代理提示词具备：\n1. **聚焦**：一个清晰的问题域\n2. **自包含**：包含理解问题所需的所有上下文\n3. **明确输出**：说明代理应该返回什么\n\n```markdown\nFix the 3 failing tests in src\u002Fagents\u002Fagent-tool-abort.test.ts:\n\n1. \"should abort tool with partial output capture\" - expects 'interrupted at' in message\n2. \"should handle mixed completed and aborted tools\" - fast tool aborted instead of completed\n3. \"should properly track pendingToolCount\" - expects 3 results but gets 0\n\nThese are timing\u002Frace condition issues. Your task:\n\n1. Read the test file and understand what each test verifies\n2. Identify root cause - timing issues or actual bugs?\n3. Fix by:\n   - Replacing arbitrary timeouts with event-based waiting\n   - Fixing bugs in abort implementation if found\n   - Adjusting test expectations if testing changed behavior\n\nDo NOT just increase timeouts - find the real issue.\n\nReturn: Summary of what you found and what you fixed.\n```\n\n## 常见错误\n\n**❌ 太宽泛：** “修好所有测试” - 代理会迷失方向\n**✅ 具体：** “修好 agent-tool-abort.test.ts” - 范围聚焦\n\n**❌ 没有上下文：** “修好这个竞态条件” - 代理不知道在哪里\n**✅ 有上下文：** 粘贴错误消息和测试名称\n\n**❌ 没有约束：** 代理可能重构所有内容\n**✅ 有约束：** “不要修改生产代码” 或 “只修测试”\n\n**❌ 输出含糊：** “修好它” - 你不知道改了什么\n**✅ 输出具体：** “返回根因和变更总结”\n\n## 何时不要使用\n\n**相关失败：** 修一个可能修好其他，先一起调查\n**需要完整上下文：** 理解问题需要查看整个系统\n**探索性调试：** 你还不知道坏在哪里\n**共享状态：** 代理会相互干扰（编辑相同文件、使用相同资源）\n\n## 会话中的真实示例\n\n**场景：** 大型重构后，3 个文件里有 6 个测试失败\n\n**失败：**\n- agent-tool-abort.test.ts：3 个失败（计时问题）\n- batch-completion-behavior.test.ts：2 个失败（工具未执行）\n- tool-approval-race-conditions.test.ts：1 个失败（execution count = 0）\n\n**决策：** 问题域独立：中止逻辑、批量完成、竞态条件彼此分离\n\n**派发：**\n```\nAgent 1 → Fix agent-tool-abort.test.ts\nAgent 2 → Fix batch-completion-behavior.test.ts\nAgent 3 → Fix tool-approval-race-conditions.test.ts\n```\n\n**结果：**\n- Agent 1：用基于事件的等待替换超时\n- Agent 2：修复事件结构 bug（threadId 放错位置）\n- Agent 3：增加等待，让异步工具执行完成\n\n**集成：** 所有修复彼此独立、无冲突、完整套件通过\n\n**节省时间：** 3 个问题并行解决，而不是串行处理\n\n## 主要收益\n\n1. **并行化**：多个调查同时进行\n2. **聚焦**：每个代理范围窄，需跟踪的上下文更少\n3. **独立性**：代理不会互相干扰\n4. **速度**：用处理 1 个问题的时间解决 3 个问题\n\n## 验证\n\n代理返回后：\n1. **审阅每份总结**：理解改了什么\n2. **检查冲突**：代理是否编辑了相同代码？\n3. **运行完整套件**：验证所有修复能一起工作\n4. **抽查**：代理可能犯系统性错误\n5. **写回状态**：用 `update_plan` 和报告记录最终状态；如果本轮已选择 mcp-orch，再用 `task_update_node` 写入对应 node。\n\n## 真实影响\n\n来自调试会话（2025-10-03）：\n- 3 个文件里有 6 个失败\n- 并行派发 3 个代理\n- 所有调查并发完成\n- 所有修复成功集成\n- 代理变更之间零冲突\n","# 调度并行代理\n\n## 概览\n\n你会把任务委派给拥有隔离上下文的专门代理。通过精确编写它们的指令和上下文，你可以确保它们保持聚焦并完成任务。它们不应该继承你的会话上下文或历史；你要只构造它们需要的内容。这也能保留你自己的上下文，用于协调工作。\n\n当你有多个无关失败（不同测试文件、不同子系统、不同 bug）时，逐个调查会浪费时间。每个调查都独立，可以并行进行。\n\n**核心原则：** 每个独立问题域派发一个代理。让它们并发工作。\n\n**super-agent-v3 编排选择：** 并行代理不强制绑定 mcp-orch。优先使用当前平台可用的原生多代理能力；只有需要持久 DAG、重试、租约、cron\u002Fwakeup 或结构化交接记录时，才可选使用 `task_create_dag`、`task_start_dag`、`task_dispatch_node`、`task_update_node`。缺少 mcp-go-agent-orchestration 工具不是阻断条件；继续使用可用的子代理能力，或在不适合派发时改为单代理只读分析并说明观测限制。\n\n## 何时使用\n\n```dot\ndigraph when_to_use {\n    \"Multiple failures?\" [shape=diamond];\n    \"Are they independent?\" [shape=diamond];\n    \"Single agent investigates all\" [shape=box];\n    \"One agent per problem domain\" [shape=box];\n    \"Can they work in parallel?\" [shape=diamond];\n    \"Sequential agents\" [shape=box];\n    \"Parallel dispatch\" [shape=box];\n\n    \"Multiple failures?\" -> \"Are they independent?\" [label=\"yes\"];\n    \"Are they independent?\" -> \"Single agent investigates all\" [label=\"no - related\"];\n    \"Are they independent?\" -> \"Can they work in parallel?\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Parallel dispatch\" [label=\"yes\"];\n    \"Can they work in parallel?\" -> \"Sequential agents\" [label=\"no - shared state\"];\n}\n```\n\n**适用场景：**\n- 3 个以上测试文件失败，且根因不同\n- 多个子系统独立损坏\n- 每个问题不需要其他问题的上下文就能理解\n- 调查之间没有共享状态\n\n**不适用场景：**\n- 失败彼此相关（修复一个可能修复其他）\n- 需要理解完整系统状态\n- 代理会相互干扰\n\n## 模式\n\n### 1. 识别独立域\n\n按损坏内容分组失败：\n- 文件 A 测试：工具批准流程\n- 文件 B 测试：批量完成行为\n- 文件 C 测试：中止功能\n\n每个域都是独立的：修复工具批准不会影响中止测试。\n\n### 2. 创建聚焦的代理任务\n\n每个代理得到：\n- **具体范围：** 一个测试文件或子系统\n- **明确目标：** 让这些测试通过\n- **约束：** 不要修改其他代码\n- **预期输出：** 总结发现和修复内容\n\n### 3. 并行派发\n\n平台原生多代理可直接派发。若本轮明确选择 mcp-orch 记录持久编排状态，可按下面方式建 DAG：\n\n```typescript\ntask_create_dag({\n  dag_key: \"fix-independent-test-failures\",\n  nodes: [\n    { node_key: \"agent-tool-abort\", assigned_to: \"worker\", depends_on: [] },\n    { node_key: \"batch-completion\", assigned_to: \"worker\", depends_on: [] },\n    { node_key: \"tool-approval-race\", assigned_to: \"worker\", depends_on: [] }\n  ]\n})\ntask_start_dag(\"fix-independent-test-failures\")\ntask_dispatch_node(\"agent-tool-abort\", run_id, assigned_to)\ntask_dispatch_node(\"batch-completion\", run_id, assigned_to)\ntask_dispatch_node(\"tool-approval-race\", run_id, assigned_to)\n```\n\n如果使用平台原生多代理，保留每个子代理的范围、返回摘要、文件改动和验证结果；不需要伪造 DAG\u002Fnode 证据。\n\n### 4. 审阅并集成\n\n代理返回后：\n- 阅读每份总结\n- 验证修复之间没有冲突\n- 运行完整测试套件\n- 集成所有变更\n\n## 代理提示词结构\n\n好的代理提示词具备：\n1. **聚焦**：一个清晰的问题域\n2. **自包含**：包含理解问题所需的所有上下文\n3. **明确输出**：说明代理应该返回什么\n\n```markdown\nFix the 3 failing tests in src\u002Fagents\u002Fagent-tool-abort.test.ts:\n\n1. \"should abort tool with partial output capture\" - expects 'interrupted at' in message\n2. \"should handle mixed completed and aborted tools\" - fast tool aborted instead of completed\n3. \"should properly track pendingToolCount\" - expects 3 results but gets 0\n\nThese are timing\u002Frace condition issues. Your task:\n\n1. Read the test file and understand what each test verifies\n2. Identify root cause - timing issues or actual bugs?\n3. Fix by:\n   - Replacing arbitrary timeouts with event-based waiting\n   - Fixing bugs in abort implementation if found\n   - Adjusting test expectations if testing changed behavior\n\nDo NOT just increase timeouts - find the real issue.\n\nReturn: Summary of what you found and what you fixed.\n```\n\n## 常见错误\n\n**❌ 太宽泛：** “修好所有测试” - 代理会迷失方向\n**✅ 具体：** “修好 agent-tool-abort.test.ts” - 范围聚焦\n\n**❌ 没有上下文：** “修好这个竞态条件” - 代理不知道在哪里\n**✅ 有上下文：** 粘贴错误消息和测试名称\n\n**❌ 没有约束：** 代理可能重构所有内容\n**✅ 有约束：** “不要修改生产代码” 或 “只修测试”\n\n**❌ 输出含糊：** “修好它” - 你不知道改了什么\n**✅ 输出具体：** “返回根因和变更总结”\n\n## 何时不要使用\n\n**相关失败：** 修一个可能修好其他，先一起调查\n**需要完整上下文：** 理解问题需要查看整个系统\n**探索性调试：** 你还不知道坏在哪里\n**共享状态：** 代理会相互干扰（编辑相同文件、使用相同资源）\n\n## 会话中的真实示例\n\n**场景：** 大型重构后，3 个文件里有 6 个测试失败\n\n**失败：**\n- agent-tool-abort.test.ts：3 个失败（计时问题）\n- batch-completion-behavior.test.ts：2 个失败（工具未执行）\n- tool-approval-race-conditions.test.ts：1 个失败（execution count = 0）\n\n**决策：** 问题域独立：中止逻辑、批量完成、竞态条件彼此分离\n\n**派发：**\n```\nAgent 1 → Fix agent-tool-abort.test.ts\nAgent 2 → Fix batch-completion-behavior.test.ts\nAgent 3 → Fix tool-approval-race-conditions.test.ts\n```\n\n**结果：**\n- Agent 1：用基于事件的等待替换超时\n- Agent 2：修复事件结构 bug（threadId 放错位置）\n- Agent 3：增加等待，让异步工具执行完成\n\n**集成：** 所有修复彼此独立、无冲突、完整套件通过\n\n**节省时间：** 3 个问题并行解决，而不是串行处理\n\n## 主要收益\n\n1. **并行化**：多个调查同时进行\n2. **聚焦**：每个代理范围窄，需跟踪的上下文更少\n3. **独立性**：代理不会互相干扰\n4. **速度**：用处理 1 个问题的时间解决 3 个问题\n\n## 验证\n\n代理返回后：\n1. **审阅每份总结**：理解改了什么\n2. **检查冲突**：代理是否编辑了相同代码？\n3. **运行完整套件**：验证所有修复能一起工作\n4. **抽查**：代理可能犯系统性错误\n5. **写回状态**：用 `update_plan` 和报告记录最终状态；如果本轮已选择 mcp-orch，再用 `task_update_node` 写入对应 node。\n\n## 真实影响\n\n来自调试会话（2025-10-03）：\n- 3 个文件里有 6 个失败\n- 并行派发 3 个代理\n- 所有调查并发完成\n- 所有修复成功集成\n- 代理变更之间零冲突\n",{"name":5,"aliases":27,"description":7},[28,29,30],"@调度并行代理","@并行代理调度","@parallel-agent-orchestration","main","287849f4ce06aaaa7e8f517126f73b016043d332",".agent\u002Fskills\u002F调度并行代理","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud","2026-10-11 02:13:17",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add lihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit --skill \"调度并行代理\"",{"tool":43,"command":44},"bunx","bunx skills add lihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit --skill \"调度并行代理\"",{"tool":46,"command":47},"pnpm","pnpm dlx skills add lihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit --skill \"调度并行代理\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002F调度并行代理\u002FSKILL.md",true,[],[52,82,98,121,137,151],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":63,"publishedAt":22},"01M6GK59PDCBRZQ6D03BGXM8XM","mcp-lsp-project-config","配置、安装、检查、修复或迁移项目级 mcp-lsp stdio MCP，覆盖 Codex、Claude Code 和 Google Antigravity，以及 Windows 原生、WSL 原生和 Windows 宿主通过 wsl.exe 桥接 Linux sidecar 的自动选型。用户提到项目 MCP、LSP MCP、.codex\u002Fconfig.toml、.mcp.json、.agents\u002Fmcp_config.json、Codex 中 LSP 工具有时直接暴露有时只在延迟工具目录、ALL_TOOLS 过滤为空、工具已显示但调用报 client is closing、EOF、Transport closed，或希望三个客户端共用仓库内 mcp-lsp 时使用。","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002Fbin\u002FLSP\u002Fmcp-lsp-project-config-skill\u002FSKILL.md",[58],{"categoryNo":59,"categoryName":60,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81],"mcp lsp project config","MCP","config","lsp","project","mcp lsp","google","linux","antigravity","codex","windows","code","Tools","json","toml","client","工具","closing",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":22},"01M6GK57H2A7XK3QZ00HCV9XM0","注释规范","当在 super-agent-v3 中编写或审查 Go 函数级中文注释、React hooks\u002Fservice\u002Fcontroller 注释，或处理注释守卫失败时使用。","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002F注释规范\u002FSKILL.md",[],[84,89,90,91,92,93,94,95,96,97],"go","react","controller","中文","hooks","service","v3","react hooks","comments",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":107,"publishedAt":22},"01M6GK545MTTE5X1Q4NF92PNRN","字段守卫","当新增、删除、重命名或跨层传递结构化字段，以及修改 DTO、mapper、schema、API\u002FRPC、事件、配置、store、序列化或前后端契约时自动使用；追踪生产源到全部消费端并建立 fail-fast 字段守卫。","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002F字段守卫\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000010","后端与接口",[100,108,109,110,111,112,66,113,114,115,116,117,118,119,120],"后端","event","payload","store","mapping","rpc","fast","api","guard","消费","schema","drift","contract",{"skillNo":122,"name":108,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":128,"publishedAt":22},"01M6GK50VVC89B3MMSTKBG76ZS","在 super-agent-v3 中编写、审查或重构 Go 后端代码时使用。","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002F后端\u002FSKILL.md",[126,127],{"categoryNo":105,"categoryName":106,"taxonomyType":61,"taxonomyTypeDesc":62},{"categoryNo":59,"categoryName":60,"taxonomyType":61,"taxonomyTypeDesc":62},[108,129,130,131,132,89,65,133,134,135,95,136,111],"sqlc","backend","cmd","golang","runner","platform","module","fx",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":22},"01M6GK4YP5DTSBD02AF8YSRNME","前端","当在 super-agent-v3 中开发、审查或修复当前 React\u002FVite 前端 UI 时使用；前端源码只在 frontend-app。","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002F前端\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000009","前端开发",[147,148,149,95,150,90],"frontend","vite","app","ui",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":22},"01M6GK4WWB9A6N51VPCZHC3NB1","全量项目地图生成","当在 super-agent-v3 中生成、更新或校验 docs\u002Fdoc\u002Fcodemap 项目地图、AI index 或能力清单时使用。","https:\u002F\u002Fgithub.com\u002Flihah111222333-cloud\u002FSuper-Dolphin-Agent-Cockpit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002F全量项目地图生成\u002FSKILL.md",[],[153,158,159,95,160,161,162,163,164],"地图","生成","codemap","校验","doc","index","docs"]