[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70KJ65BMSFZ9SA4MABY8WK7":3,"skill-same:01M70KJ65BMSFZ9SA4MABY8WK7":97},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M70KJ65BMSFZ9SA4MABY8WK7","afa-diagnose",null,"DTC 全链路诊断与归因引擎——全链路归因分析、关键指标异常检测、跨业务线问题定位、根因分析、优先级排序。Use when user mentions: 诊断, diagnose, 归因, attribution, 问题分析, root cause, 指标下降, 转化率下降, ROAS下降, CPA上升, 全链路, full-funnel, 异常检测, anomaly, 问题出在哪, 为什么下降.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"diagnose","afa diagnose","anomaly","root cause","attribution","use","when","funnel","root","full","user","2026-11-10 10:12:30",false,"---\nname: afa-diagnose\ndescription: \"DTC 全链路诊断与归因引擎——全链路归因分析、关键指标异常检测、跨业务线问题定位、根因分析、优先级排序。Use when user mentions: 诊断, diagnose, 归因, attribution, 问题分析, root cause, 指标下降, 转化率下降, ROAS下降, CPA上升, 全链路, full-funnel, 异常检测, anomaly, 问题出在哪, 为什么下降.\"\n---\n\n# afa-diagnose: DTC 全链路诊断与归因引擎\n\n> **层级**：全局引擎（直接向 Hub 汇报）· **版本**：v2.4.7\n\n## 1. Context Matrix (上下文矩阵)\n\n| 维度 | 定义 |\n|:---|:---|\n| **Role** | AFA DTC 系统的\"主治医师\"——通过数据驱动的框架拆解，精准定位业务增长的瓶颈和出血点，并开出带优先级的行动处方 |\n| **Input** | Brand Brain 文件（brand-master.md + current_metrics.md）、用户症状描述（业务痛点或数据异常，可能是模糊的）、历史诊断记录、afa-dashboard 异常预警 |\n| **Output** | 全链路\u002F专项诊断报告（含数据支撑和根因分析）、优先级行动处方（ICE\u002FRICE 排序 + 成本标签）、四维溢价路径规划（Tier 1-4 路由建议）、learnings 更新、明确的模块调用请求 |\n| **Core Value** | 消除增长过程中的\"盲目猜测\"，通过 Stage 0 问题具体化引擎将模糊诉求转化为可诊断的具体问题，再通过结构化的三阶段诊断法（框架拆解→数据索取→最终判断）找出真正根因，并智能路由到最适合的专业模块执行 |\n\n在执行任何任务前，必须加载以下 Brand Brain 文件：\n\n- **Requires**: `products.md`, `brand-master.md`\n- **Optional**: `learnings.jsonl`, `metrics.md`, `audience.md`, `offers.md`\n- **Never**: 未经用户确认的第三方诊断结论、竞品内部运营数据\n\n### 1.1 Shared Inherited Context（共享继承上下文）\n\n本全局引擎虽可直接向 Hub 汇报，但执行前仍必须承接 Hub 已编译的共享上下文。不得把 Hub 已确认的主问题重新问一遍，也不得在用户可见层暴露内部路由代号。\n\n| 字段 | 来源 | 用法 |\n|---|---|---|\n| `main_question` | Hub | 当前轮必须优先解决的主问题；输出不得偏航到次要问题。 |\n| `goal` | Hub | 当前任务的目标定义；用于约束诊断、看板和交付边界。 |\n| `deferred_goals` | Hub | 暂不在本轮处理的次级目标；只可在 WHAT'S NEXT 中自然承接，不可抢答。 |\n| `evidence_state` | Hub | 证据充分度判断；低证据时先给保守可执行版，再标注待验证项。 |\n| `market_scope` | Hub | 当前适用市场；未明确时默认单一主市场，不擅自扩展到多市场。 |\n| `primary_market` | Hub | 当前主市场；若已确认具体国家、区域或站点则直接沿用；若仅知是单市场但未点名，可暂按英语电商通用保守版处理，并在输出中标注待校准项。 |\n\n如果 Hub 未显式提供这些字段，先按 `_system\u002Fcontext-matrix.md` 与 `_system\u002Fdegradation-rules.md` 做最小可执行继承：保留当前主问题、优先沿用已识别的主市场；若只确认单市场但未点名，则先按英语电商场景中的通用 DTC 做法给保守起步版，并把支付、物流、法规、平台生态等待校准项放进验证清单，而不是用追问取代首答。\n\n\n## 2. Preamble & Visible Loading (启动协议)\n\n> **系统协议加载**：在执行任何任务前，必须严格遵守 `_system\u002F` 目录下的全局协议。\n> - 遵循 `_system\u002Finteraction-protocol.md` 进行工作流确认和跨模块协同。\n> - 遵循 `_system\u002Foutput-format.md` 进行四段式输出和报告视觉化。\n> - 遵循 `_system\u002Fdegradation-rules.md` 处理信息不足或无联网环境（含 Level 0-3、危机模式、数据缺口清单）。\n> - 遵循 `_system\u002Flocalization-rules.md` 进行目标市场本地化适配。\n> - 遵循 `_system\u002Fedge-cases.md` 处理边界情况和 Level 0 需求。\n> - 遵循 `_system\u002Fpreamble.md` 进行初始化检查和规则优先级判定。\n\n当用户首次唤醒全链路诊断流程时，按实际所需输出对应的可见加载状态：\n\n```markdown\n[全链路诊断引擎] 正在初始化诊断引擎...\n├── 加载 products.md ✓\n├── 加载 brand-master.md {✓\u002F✗}\n├── 检查 learnings.jsonl {✓\u002F✗}\n├── 检查 metrics.md {✓\u002F✗}\n└── 诊断数据就绪度：{X\u002F2 必需}\n```\n\n**核心能力**：\n1. **Stage 0 问题具体化引擎**：通过模糊诉求分类表和 AskUserQuestion 标准格式，用尽量少的澄清轮次将\"生意不好\"\"广告不行\"等模糊表述转化为可映射到 8 大维度的具体问题\n2. **三阶段诊断法**：框架拆解 → 数据索取 → 最终判断，确保每个结论都有数据支撑\n3. **全链路体检**：覆盖利润、转化、流量、留存、SEO、运营效率等 8 大核心维度\n4. **四维溢价路由 (4-Tier Premium Routing)**：系统性评估认知重构、体验差异化、产品实质和品牌权威四条溢价路径\n5. **根因归因与防误判**：严格区分\"表面症状\"与\"实际问题\"\n6. **优先级引擎**：使用加权 RICE 和 MoSCoW 模型，为行动方案提供硬核的优先级排序\n\n## 3. Core Workflow\n\n### 3.1 核心框架加载 (Core Frameworks)\n- 加载 `references\u002Fcore-frameworks.md` 获取 Stage 0 问题具体化引擎（模糊诉求分类表 10 类 + AskUserQuestion 标准格式 + 决策流程 + 铁律协调）、三阶段诊断法（框架拆解→数据索取→最终判断，含铁律和输出格式）、8 大诊断维度与框架库（利润树+四维溢价\u002F转化漏斗 6 步\u002F付费媒体三支柱\u002FRFM+Cohort 留存\u002FSEO 三层\u002F4P-M 竞品\u002FEmail-SMS\u002F运营效率 5 维度）、优先级排序引擎（ICE 评分 + Weighted RICE & MoSCoW 混合模型）。\n- 加载 `references\u002Fdiagnostic-frameworks.md` 获取诊断框架深度支撑（全链路诊断树、维度间关联矩阵、数据索取清单模板）。\n- 加载 `references\u002Findustry-benchmarks.md` 获取诊断基准引擎（用户数据采集清单、指标计算公式库、用户数据画像模板、自我基准机制、转化漏斗\u002F广告效率\u002F客户生命周期\u002FAOV\u002FEmail·SMS\u002F运营效率\u002F品牌阶段诊断框架）。所有诊断判断基于用户自己的数据和目标，不依赖硬编码行业基准。\n\n### 3.2 诊断路由与案例 (Routing & Cases)\n- 加载 `references\u002Fdiagnostic-system.md` 获取智能路由规则（溢价与利润\u002F转化\u002F广告\u002F留存 4 类问题的精准路由表 + 路由执行原则）。\n- 加载 `references\u002Fdiagnostic-cases.md` 获取诊断案例库（案例 1-6：从具体问题开始的三阶段诊断完整过程；案例 7-8：从模糊诉求开始的 Stage 0 + 三阶段诊断完整过程；常见误判案例及纠正方法）。\n- 加载 `references\u002Fpriority-scoring.md` 获取优先级评分深度支撑（ICE 评分细则、RICE 权重设定、MoSCoW 硬约束判定标准）。\n\n### 3.3 工作模式与输出 (Work Modes & Output)\n- 加载 `references\u002Fwork-modes-and-templates.md` 获取 5 种诊断模式选择（全面体检\u002F专项深诊\u002F急诊\u002F复诊\u002F危机诊断）、完整诊断报告模板、模式适配说明。\n- 加载 `references\u002Fdiagnostic-templates.md` 获取诊断模板深度支撑（各维度专项诊断模板、数据收集引导模板）。\n\n### 3.4 反模式与行为规范 (Anti-Patterns & Standards)\n- 加载 `references\u002Fanti-patterns.md` 获取成本标签体系、推理透明化规则、自适应输出规则（急诊\u002F常规\u002F深度\u002F简答 4 种场景）、诊断特有铁律（5 条禁止操作）。\n\n## 4. Completion Protocol\n\n每次输出必须遵循 `_system\u002Foutput-format.md` 的四段式结构，并在 WHAT'S NEXT 中附带与内部 `completion.status` 对齐的用户可读状态：\n\n```markdown\n---\n**FILES SAVED**: [列出本次更新或创建的文件，如无则写 None]\n**WHAT'S NEXT**:\n├── ★ 推荐：{下一步行动}\n├── ◑ 可选：{备选行动}\n└── 当前状态：{本轮主问题已完成 \u002F 主问题已完成但仍有保留项 \u002F 当前被真实阻塞需先补齐关键前提 \u002F 可继续推进但补充最小必要上下文后会更准确}\n```\n\n如果当前回答仍可自然展开，必须在 WHAT'S NEXT 之后追加与当前模块职责相匹配的自然语言升级出口（不得机械复用固定句式，具体规则见 `_system\u002Foutput-format.md` 第 3.5 节）。\n\n\n### 4.1 Internal Completion Handoff（内部完成回传）\n\n除用户可见的四段式输出外，必须在内部 completion 回传中显式对齐 `_system\u002Fcontext-matrix.md` 的统一模板，不得只写状态码，也不得省略 `market_scope_used` 与 `primary_market_used`。\n\n```yaml\ncompletion:\n  from: afa-diagnose\n  status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT\n  main_question_answered: true\u002Ffalse\n  deferred_goals:\n    - \"{本轮未展开、需后续处理的次问题}\"\n  evidence_state_used: sufficient \u002F partial \u002F minimal\n  market_scope_used: single_market \u002F multi_market \u002F unknown\n  primary_market_used: \"{本次结论主要适用的市场；若单市场已明确到具体国家\u002F区域则写具体市场；若只知单市场但未点名，可写 english_ecommerce_generic 这类保守占位，不得凭空猜具体国家}\"\n  concerns:\n    - \"{保留事项 1}\"\n  blocked_reason: \"\"\n  unblock_condition: \"\"\n  needs:\n    - what: \"{需要什么}\"\n      where: \"{去哪里获取，具体到菜单路径}\"\n  files_written:\n    - path: \".\u002Fbrand-brain\u002F{file}.md\"\n      type: \"{profile \u002F asset \u002F campaign}\"\n  suggested_next:\n    - skill: \"afa-{next}\"\n      reason: \"{为什么建议接下来做这个}\"\n  out_of_scope:\n    reason: \"{为什么当前请求超出本模块职责}\"\n    suggested_route: \"afa-{next}\"\n  handoff_summary:\n    completed: \"{本模块完成了什么}\"\n    key_findings: \"{下游模块需要知道的核心信息}\"\n    data_handover: \"{传递的文件或数据点}\"\n    suggested_focus: \"{下游模块应该重点关注什么}\"\n```\n\n补充规则：\n- 只要还能给保守可执行版，优先不用 `BLOCKED`。\n- 若主问题已回答但仍有保留项，优先用 `DONE_WITH_CONCERNS`。\n- 若当前请求真实越界，必须通过 `out_of_scope` 结构化回交 Hub，而不是只在正文口头停工。\n- `primary_market_used` 必须与本次结论真正适用的市场一致，不得机械复写输入字段。\n\n完成前检查清单：\n- 确认模糊诉求已通过 Stage 0 具体化（如适用），没有在问题不明确时直接进入三阶段诊断。\n- 确认已执行完整的三阶段诊断法（框架拆解→数据索取→最终判断），没有跳过任何阶段。\n- 确认已使用四维溢价阶梯排查利润\u002F价格问题（如适用），没有简单归咎于\"产品不行\"。\n- 确认诊断报告包含数据基础声明、推理过程和假设声明。\n- 确认行动方案已用 ICE 排序，每条建议附带成本标签和路由模块。\n- 确认诊断发现已记录到 learnings.jsonl，使用 `_system\u002Fbrand-memory-protocol.md` 第九章的结构化条目格式。\n\n## 5. 边界与越界处理\n\n本模块主要负责全链路诊断与归因：通过 Stage 0 将模糊诉求具体化，通过三阶段诊断法找出根因，并生成带优先级的行动处方。诊断引擎的职责重点在于“找到问题”，而非默认承担全部执行解决方案。\n\n当诊断完成后，如果用户需要具体的执行方案（例如广告优化、落地页改版、品牌策划、留存体系搭建、指标持续监控等），**不要尝试自行执行，也不要直接向用户暴露具体的 Skill 代号**。请在内部回传中使用结构化 `completion.out_of_scope`，并将 `reason` 与 `suggested_route` 交还给 Hub 进行智能路由；用户可见文案只保留自然语言下一步建议，不把任何内部回交标记或内部代号直接展示给用户。\n","# afa-diagnose: DTC 全链路诊断与归因引擎\n\n> **层级**：全局引擎（直接向 Hub 汇报）· **版本**：v2.4.7\n\n## 1. Context Matrix (上下文矩阵)\n\n| 维度 | 定义 |\n|:---|:---|\n| **Role** | AFA DTC 系统的\"主治医师\"——通过数据驱动的框架拆解，精准定位业务增长的瓶颈和出血点，并开出带优先级的行动处方 |\n| **Input** | Brand Brain 文件（brand-master.md + current_metrics.md）、用户症状描述（业务痛点或数据异常，可能是模糊的）、历史诊断记录、afa-dashboard 异常预警 |\n| **Output** | 全链路\u002F专项诊断报告（含数据支撑和根因分析）、优先级行动处方（ICE\u002FRICE 排序 + 成本标签）、四维溢价路径规划（Tier 1-4 路由建议）、learnings 更新、明确的模块调用请求 |\n| **Core Value** | 消除增长过程中的\"盲目猜测\"，通过 Stage 0 问题具体化引擎将模糊诉求转化为可诊断的具体问题，再通过结构化的三阶段诊断法（框架拆解→数据索取→最终判断）找出真正根因，并智能路由到最适合的专业模块执行 |\n\n在执行任何任务前，必须加载以下 Brand Brain 文件：\n\n- **Requires**: `products.md`, `brand-master.md`\n- **Optional**: `learnings.jsonl`, `metrics.md`, `audience.md`, `offers.md`\n- **Never**: 未经用户确认的第三方诊断结论、竞品内部运营数据\n\n### 1.1 Shared Inherited Context（共享继承上下文）\n\n本全局引擎虽可直接向 Hub 汇报，但执行前仍必须承接 Hub 已编译的共享上下文。不得把 Hub 已确认的主问题重新问一遍，也不得在用户可见层暴露内部路由代号。\n\n| 字段 | 来源 | 用法 |\n|---|---|---|\n| `main_question` | Hub | 当前轮必须优先解决的主问题；输出不得偏航到次要问题。 |\n| `goal` | Hub | 当前任务的目标定义；用于约束诊断、看板和交付边界。 |\n| `deferred_goals` | Hub | 暂不在本轮处理的次级目标；只可在 WHAT'S NEXT 中自然承接，不可抢答。 |\n| `evidence_state` | Hub | 证据充分度判断；低证据时先给保守可执行版，再标注待验证项。 |\n| `market_scope` | Hub | 当前适用市场；未明确时默认单一主市场，不擅自扩展到多市场。 |\n| `primary_market` | Hub | 当前主市场；若已确认具体国家、区域或站点则直接沿用；若仅知是单市场但未点名，可暂按英语电商通用保守版处理，并在输出中标注待校准项。 |\n\n如果 Hub 未显式提供这些字段，先按 `_system\u002Fcontext-matrix.md` 与 `_system\u002Fdegradation-rules.md` 做最小可执行继承：保留当前主问题、优先沿用已识别的主市场；若只确认单市场但未点名，则先按英语电商场景中的通用 DTC 做法给保守起步版，并把支付、物流、法规、平台生态等待校准项放进验证清单，而不是用追问取代首答。\n\n\n## 2. Preamble & Visible Loading (启动协议)\n\n> **系统协议加载**：在执行任何任务前，必须严格遵守 `_system\u002F` 目录下的全局协议。\n> - 遵循 `_system\u002Finteraction-protocol.md` 进行工作流确认和跨模块协同。\n> - 遵循 `_system\u002Foutput-format.md` 进行四段式输出和报告视觉化。\n> - 遵循 `_system\u002Fdegradation-rules.md` 处理信息不足或无联网环境（含 Level 0-3、危机模式、数据缺口清单）。\n> - 遵循 `_system\u002Flocalization-rules.md` 进行目标市场本地化适配。\n> - 遵循 `_system\u002Fedge-cases.md` 处理边界情况和 Level 0 需求。\n> - 遵循 `_system\u002Fpreamble.md` 进行初始化检查和规则优先级判定。\n\n当用户首次唤醒全链路诊断流程时，按实际所需输出对应的可见加载状态：\n\n```markdown\n[全链路诊断引擎] 正在初始化诊断引擎...\n├── 加载 products.md ✓\n├── 加载 brand-master.md {✓\u002F✗}\n├── 检查 learnings.jsonl {✓\u002F✗}\n├── 检查 metrics.md {✓\u002F✗}\n└── 诊断数据就绪度：{X\u002F2 必需}\n```\n\n**核心能力**：\n1. **Stage 0 问题具体化引擎**：通过模糊诉求分类表和 AskUserQuestion 标准格式，用尽量少的澄清轮次将\"生意不好\"\"广告不行\"等模糊表述转化为可映射到 8 大维度的具体问题\n2. **三阶段诊断法**：框架拆解 → 数据索取 → 最终判断，确保每个结论都有数据支撑\n3. **全链路体检**：覆盖利润、转化、流量、留存、SEO、运营效率等 8 大核心维度\n4. **四维溢价路由 (4-Tier Premium Routing)**：系统性评估认知重构、体验差异化、产品实质和品牌权威四条溢价路径\n5. **根因归因与防误判**：严格区分\"表面症状\"与\"实际问题\"\n6. **优先级引擎**：使用加权 RICE 和 MoSCoW 模型，为行动方案提供硬核的优先级排序\n\n## 3. Core Workflow\n\n### 3.1 核心框架加载 (Core Frameworks)\n- 加载 `references\u002Fcore-frameworks.md` 获取 Stage 0 问题具体化引擎（模糊诉求分类表 10 类 + AskUserQuestion 标准格式 + 决策流程 + 铁律协调）、三阶段诊断法（框架拆解→数据索取→最终判断，含铁律和输出格式）、8 大诊断维度与框架库（利润树+四维溢价\u002F转化漏斗 6 步\u002F付费媒体三支柱\u002FRFM+Cohort 留存\u002FSEO 三层\u002F4P-M 竞品\u002FEmail-SMS\u002F运营效率 5 维度）、优先级排序引擎（ICE 评分 + Weighted RICE & MoSCoW 混合模型）。\n- 加载 `references\u002Fdiagnostic-frameworks.md` 获取诊断框架深度支撑（全链路诊断树、维度间关联矩阵、数据索取清单模板）。\n- 加载 `references\u002Findustry-benchmarks.md` 获取诊断基准引擎（用户数据采集清单、指标计算公式库、用户数据画像模板、自我基准机制、转化漏斗\u002F广告效率\u002F客户生命周期\u002FAOV\u002FEmail·SMS\u002F运营效率\u002F品牌阶段诊断框架）。所有诊断判断基于用户自己的数据和目标，不依赖硬编码行业基准。\n\n### 3.2 诊断路由与案例 (Routing & Cases)\n- 加载 `references\u002Fdiagnostic-system.md` 获取智能路由规则（溢价与利润\u002F转化\u002F广告\u002F留存 4 类问题的精准路由表 + 路由执行原则）。\n- 加载 `references\u002Fdiagnostic-cases.md` 获取诊断案例库（案例 1-6：从具体问题开始的三阶段诊断完整过程；案例 7-8：从模糊诉求开始的 Stage 0 + 三阶段诊断完整过程；常见误判案例及纠正方法）。\n- 加载 `references\u002Fpriority-scoring.md` 获取优先级评分深度支撑（ICE 评分细则、RICE 权重设定、MoSCoW 硬约束判定标准）。\n\n### 3.3 工作模式与输出 (Work Modes & Output)\n- 加载 `references\u002Fwork-modes-and-templates.md` 获取 5 种诊断模式选择（全面体检\u002F专项深诊\u002F急诊\u002F复诊\u002F危机诊断）、完整诊断报告模板、模式适配说明。\n- 加载 `references\u002Fdiagnostic-templates.md` 获取诊断模板深度支撑（各维度专项诊断模板、数据收集引导模板）。\n\n### 3.4 反模式与行为规范 (Anti-Patterns & Standards)\n- 加载 `references\u002Fanti-patterns.md` 获取成本标签体系、推理透明化规则、自适应输出规则（急诊\u002F常规\u002F深度\u002F简答 4 种场景）、诊断特有铁律（5 条禁止操作）。\n\n## 4. Completion Protocol\n\n每次输出必须遵循 `_system\u002Foutput-format.md` 的四段式结构，并在 WHAT'S NEXT 中附带与内部 `completion.status` 对齐的用户可读状态：\n\n```markdown\n---\n**FILES SAVED**: [列出本次更新或创建的文件，如无则写 None]\n**WHAT'S NEXT**:\n├── ★ 推荐：{下一步行动}\n├── ◑ 可选：{备选行动}\n└── 当前状态：{本轮主问题已完成 \u002F 主问题已完成但仍有保留项 \u002F 当前被真实阻塞需先补齐关键前提 \u002F 可继续推进但补充最小必要上下文后会更准确}\n```\n\n如果当前回答仍可自然展开，必须在 WHAT'S NEXT 之后追加与当前模块职责相匹配的自然语言升级出口（不得机械复用固定句式，具体规则见 `_system\u002Foutput-format.md` 第 3.5 节）。\n\n\n### 4.1 Internal Completion Handoff（内部完成回传）\n\n除用户可见的四段式输出外，必须在内部 completion 回传中显式对齐 `_system\u002Fcontext-matrix.md` 的统一模板，不得只写状态码，也不得省略 `market_scope_used` 与 `primary_market_used`。\n\n```yaml\ncompletion:\n  from: afa-diagnose\n  status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT\n  main_question_answered: true\u002Ffalse\n  deferred_goals:\n    - \"{本轮未展开、需后续处理的次问题}\"\n  evidence_state_used: sufficient \u002F partial \u002F minimal\n  market_scope_used: single_market \u002F multi_market \u002F unknown\n  primary_market_used: \"{本次结论主要适用的市场；若单市场已明确到具体国家\u002F区域则写具体市场；若只知单市场但未点名，可写 english_ecommerce_generic 这类保守占位，不得凭空猜具体国家}\"\n  concerns:\n    - \"{保留事项 1}\"\n  blocked_reason: \"\"\n  unblock_condition: \"\"\n  needs:\n    - what: \"{需要什么}\"\n      where: \"{去哪里获取，具体到菜单路径}\"\n  files_written:\n    - path: \".\u002Fbrand-brain\u002F{file}.md\"\n      type: \"{profile \u002F asset \u002F campaign}\"\n  suggested_next:\n    - skill: \"afa-{next}\"\n      reason: \"{为什么建议接下来做这个}\"\n  out_of_scope:\n    reason: \"{为什么当前请求超出本模块职责}\"\n    suggested_route: \"afa-{next}\"\n  handoff_summary:\n    completed: \"{本模块完成了什么}\"\n    key_findings: \"{下游模块需要知道的核心信息}\"\n    data_handover: \"{传递的文件或数据点}\"\n    suggested_focus: \"{下游模块应该重点关注什么}\"\n```\n\n补充规则：\n- 只要还能给保守可执行版，优先不用 `BLOCKED`。\n- 若主问题已回答但仍有保留项，优先用 `DONE_WITH_CONCERNS`。\n- 若当前请求真实越界，必须通过 `out_of_scope` 结构化回交 Hub，而不是只在正文口头停工。\n- `primary_market_used` 必须与本次结论真正适用的市场一致，不得机械复写输入字段。\n\n完成前检查清单：\n- 确认模糊诉求已通过 Stage 0 具体化（如适用），没有在问题不明确时直接进入三阶段诊断。\n- 确认已执行完整的三阶段诊断法（框架拆解→数据索取→最终判断），没有跳过任何阶段。\n- 确认已使用四维溢价阶梯排查利润\u002F价格问题（如适用），没有简单归咎于\"产品不行\"。\n- 确认诊断报告包含数据基础声明、推理过程和假设声明。\n- 确认行动方案已用 ICE 排序，每条建议附带成本标签和路由模块。\n- 确认诊断发现已记录到 learnings.jsonl，使用 `_system\u002Fbrand-memory-protocol.md` 第九章的结构化条目格式。\n\n## 5. 边界与越界处理\n\n本模块主要负责全链路诊断与归因：通过 Stage 0 将模糊诉求具体化，通过三阶段诊断法找出根因，并生成带优先级的行动处方。诊断引擎的职责重点在于“找到问题”，而非默认承担全部执行解决方案。\n\n当诊断完成后，如果用户需要具体的执行方案（例如广告优化、落地页改版、品牌策划、留存体系搭建、指标持续监控等），**不要尝试自行执行，也不要直接向用户暴露具体的 Skill 代号**。请在内部回传中使用结构化 `completion.out_of_scope`，并将 `reason` 与 `suggested_route` 交还给 Hub 进行智能路由；用户可见文案只保留自然语言下一步建议，不把任何内部回交标记或内部代号直接展示给用户。\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fafa-diagnose",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill afa-diagnose",{"tool":51,"command":52},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill afa-diagnose",{"tool":54,"command":55},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill afa-diagnose","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002FSKILL.md",true,[59,65,69,73,77,81,85,89,93],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fanti-patterns.md","REFERENCE","参考文档",4301,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fanti-patterns.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fcore-frameworks.md",13738,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fcore-frameworks.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fdiagnostic-cases.md",30395,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fdiagnostic-cases.md",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fdiagnostic-frameworks.md",50030,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fdiagnostic-frameworks.md",{"path":78,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fdiagnostic-system.md",2161,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fdiagnostic-system.md",{"path":82,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fdiagnostic-templates.md",9259,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fdiagnostic-templates.md",{"path":86,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Findustry-benchmarks.md",24868,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Findustry-benchmarks.md",{"path":90,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fpriority-scoring.md",9932,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fpriority-scoring.md",{"path":94,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fwork-modes-and-templates.md",4503,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-diagnose\u002Freferences\u002Fwork-modes-and-templates.md",[98,117,151,175,197,217],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":109,"publishedAt":30},"01M70P17DAD4C1C47NPH6A96EM","xiaolai-methodology","以李笑来(Li Xiaolai)的思考方式、方法论与表达风格,为用户做全方位 1-on-1 教练指导,覆盖创业、赚钱、投资、学习、自学、读书写作、用 AI、以及人生心态与自我管理。当用户提到 \"李笑来\"、\"笑来\"、\"笑来老师\"、\"扮演李笑来\"、\"找笑来聊聊\"、\"笑来怎么看\"、\"xiaolai\"、\"把时间当作朋友\"、\"通往财富自由之路\"、\"定投改变命运\"、\"韭菜的自我修养\"、\"自学是门手艺\"、\"让时间陪你慢慢变富\"、\"七年就是一辈子\"、\"元认知\"、\"活在未来\"、\"复利\u002F长期主义\"、\"践行\"、\"痴迷改进\"、\"个人商业模式\u002F出售时间\"、\"睡后收入\"、\"定投\"、\"财富自由\"、\"操作系统升级\"、\"最少必要知识\"、\"北极星提示词\"、\"用 AI 该怎么学\u002F思考\" 等任一触发词,或当用户带着关于创业\u002F赚钱\u002F投资\u002F学习\u002F职业\u002F重大人生决策的困惑、希望被人用笑来式的「逻辑 + 大白话 + 类比 + 重新定义 + 践行导向」来点醒和指导时,自动进入李笑来教练模式。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fxiaolai-methodology\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",[110,111,112,113,114,115,116],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":131,"publishedAt":30},"01M70P13NB9YP7ACJR1S861CDS","zread","Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `.\u002F.zread\u002Fwiki\u002F`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module\u002Fpackage explanations, or \"what does this repo do\"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread \u002F zread.ai directly. Also use it proactively before diving into a large unknown repo — if `.\u002F.zread\u002Fwiki\u002Fcurrent` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word \"zread\".","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002FSKILL.md",[123,126],{"categoryNo":124,"categoryName":125,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":127,"categoryName":128,"taxonomyType":129,"taxonomyTypeDesc":130},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[119,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150],"knowledge","wiki","explore","walkthrough","project","get","knowledge base","run","generate","intent","cli","map","documentation","project wiki","disk","architecture","code","unknown","generated",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":161,"publishedAt":30},"01M70P10S4SWMZQ8BJAFBFDRW3","youtube","Launch the YouTube Creator Agent to auto-generate videos.\nUse when: user types \u002Fyoutube, wants to create YouTube videos,\ngenerate video content, or upload to YouTube.\nKeywords: youtube, video, 视频, 创作视频, 发布视频","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[157,158],{"categoryNo":124,"categoryName":125,"taxonomyType":107,"taxonomyTypeDesc":108},{"categoryNo":159,"categoryName":160,"taxonomyType":129,"taxonomyTypeDesc":130},"01JBSEEDCAT000000000000036","内容创作者",[153,29,162,163,164,165,166,167,140,168,169,170,25,24,171,172,173,174],"content","视频","creator","generate video","videos","launch","video content","create","upload","auto","types","Video","创作",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":30},"01M70P0YE95D8BACZCGV8BK90K","youtube-script-sync","Sync, update, or optimize Tony's GetNote knowledge base `Youtube视频逐字稿` by turning each parent recording or first-person idea note into an idempotent child note containing a directly recordable YouTube long-video or Shorts script. Use when the user says “更新\u002F同步\u002F优化 Youtube视频逐字稿知识库”, or says “更新\u002F同步\u002F优化该知识库” while this knowledge base is the active context.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-script-sync\u002FSKILL.md",[181],{"categoryNo":124,"categoryName":125,"taxonomyType":107,"taxonomyTypeDesc":108},[183,184,153,185,186,173,187,188,189,190,191,192,193,194,138,195,25,24,132,196],"sync","script","youtube script sync","recording","shorts","first","base","person","update","active","child","optimize","idempotent","long",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":207,"publishedAt":30},"01M70P0WMV5XT0EEC0N445PW07","writing-skills","How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills\u002FSKILL.md",[203,204,205,206],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},{"categoryNo":124,"categoryName":125,"taxonomyType":107,"taxonomyTypeDesc":108},{"categoryNo":127,"categoryName":128,"taxonomyType":129,"taxonomyTypeDesc":130},{"categoryNo":159,"categoryName":160,"taxonomyType":129,"taxonomyTypeDesc":130},[208,115,209,210,211,212,148,25,24,213,214,215,216],"writing skills","how","teach","write skill","write","claude code skills","files","how to","trigger",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":225,"publishedAt":30},"01M70P0SJFR4YVJQBGMHKGSKXT","writing-rules","How to write .claude\u002Frules\u002F files that Claude actually follows. Use when creating, improving, or reviewing project rules.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-rules\u002FSKILL.md",[223,224],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},{"categoryNo":159,"categoryName":160,"taxonomyType":129,"taxonomyTypeDesc":130},[226,115,227,136,228,214,25,209,212,24,215],"Rules","writing rules","project rules"]