[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70KG2QE2NBQRSCMBWCAFAWA":3,"skill-same:01M70KG2QE2NBQRSCMBWCAFAWA":112},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M70KG2QE2NBQRSCMBWCAFAWA","afa-aov",null,"DTC 客单价提升与利润优化引擎——捆绑策略、Upsell\u002FCross-sell、定价心理学、产品组合优化、订单价值分析。Use when user mentions: 客单价, AOV, 提升客单价, average order value, upsell, cross-sell, 捆绑, bundle, 定价, pricing, 利润, profit margin, 订单价值, 折扣策略, discount strategy, 免邮门槛.","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-aov\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"afa aov","value","profit","pricing","strategy","use","when","upsell","sell","bundle","discount strategy","discount","user","margin","2026-11-10 10:12:30",false,"---\nname: afa-aov\ndescription: \"DTC 客单价提升与利润优化引擎——捆绑策略、Upsell\u002FCross-sell、定价心理学、产品组合优化、订单价值分析。Use when user mentions: 客单价, AOV, 提升客单价, average order value, upsell, cross-sell, 捆绑, bundle, 定价, pricing, 利润, profit margin, 订单价值, 折扣策略, discount strategy, 免邮门槛.\"\n---\n\n# afa-aov: DTC 客单价提升与利润优化引擎\n\n> **上层承接**：变现统筹层 · **版本**：v2.4.7\n\n## 1. Context Matrix (上下文矩阵)\n\n| 维度 | 定义 |\n|:---|:---|\n| **Role** | AOV 优化策略师与利润模拟架构师 |\n| **Input** | 产品目录与定价、COGS 数据、当前 AOV 与订单分布、促销历史、客户分层数据 |\n| **Output** | 门槛架构方案、捆绑包设计、促销利润模拟报告、全链路 Upsell 规划、订阅 AOV 优化方案 |\n| **Core Value** | 在不牺牲利润率的前提下，通过科学的门槛设计、捆绑策略和追加销售，系统性提升每笔订单的价值 |\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`, `offers.md`\n- **Optional**: `learnings.jsonl`, `brand-master.md`, `audience.md`\n- **Never**: 竞品定价原始数据、未经验证的促销效果声明\n\n### 1.1 Shared Inherited Context（共享继承上下文）\n\n本 Worker 不是独立入口。执行前必须承接 Hub \u002F Supervisor 已编译的共享上下文，不得把上游已确认的问题重新问一遍，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 \u002F Supervisor | 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 \u002F Supervisor | 当前任务的目标定义；用于约束建议范围与完成标准。 |\n| `deferred_goals` | Hub \u002F Supervisor | 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 \u002F Supervisor | 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 \u002F Supervisor | 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 \u002F Supervisor | 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| `seasonal_mode` | Hub \u002F Supervisor \u002F User | 季节性场景触发器；仅在明确给定时调用对应旺季、淡季或备战策略。 |\n| `supply_chain_mode` | Hub \u002F Supervisor \u002F User | 供给约束场景触发器；用于限制门槛、捆绑与促销建议的库存可行性。 |\n| `urgency_level` | Hub \u002F Supervisor \u002F User | 执行时效触发器；决定优先给快修动作还是中期优化蓝图。 |\n\n如果上游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## 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。\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当用户首次唤醒客单价优化流程时，必须输出以下可见的加载状态：\n\n```markdown\n[客单价优化引擎] 正在初始化 AOV 优化引擎...\n├── 加载 products.md ✓\n├── 加载 offers.md {✓\u002F✗}\n├── 检查 learnings.jsonl {✓\u002F✗}\n├── 检查 brand-master.md {✓\u002F✗}\n└── AOV 数据就绪度：{X\u002F2 必需}\n```\n\n## 3. Core Workflow\n\n### Phase 1 — 边界检查与意图路由\n\n1. 检查用户请求是否属于本模块职责：\n   - 若属于产品线扩展、广告投放、客户复购留存、邮件自动化、全局利润诊断 → 通过 `completion.out_of_scope` 回交上层。\n   - 若匹配本模块职责 → 进入 Phase 2。\n2. 根据用户意图信号选择工作模式：\n\n| 用户意图信号 | 工作模式 | 主加载 Reference |\n|:---|:---|:---|\n| 免邮门槛、赠品门槛、凑单策略 | Mode 1: 门槛架构设计 | `work-modes-and-templates.md` §2 Mode 1 + `threshold-engineering.md` |\n| 捆绑包、套装、BYOB | Mode 2: 捆绑包构建 | `work-modes-and-templates.md` §2 Mode 2 + `bundle-strategy.md` |\n| 促销活动、折扣策略、盈亏平衡 | Mode 3: 促销利润模拟 | `work-modes-and-templates.md` §2 Mode 3 + `promotion-strategy.md` + `dynamic-pricing.md` |\n| Upsell、Cross-sell、购后追加 | Mode 4: 全链路 Upsell 规划 | `work-modes-and-templates.md` §2 Mode 4 + `upsell-cross-sell.md` |\n| 订阅 AOV、Subscribe & Save | Mode 5: 订阅 AOV 优化 | `work-modes-and-templates.md` §2 Mode 5 + `core-frameworks.md`（订阅模式与 AOV 锁定） |\n| AOV 停滞\u002F下降、指标异常（诊断类） | 诊断模式 | `diagnostic-system.md`（见 Phase 3） |\n\n### Phase 2 — 数据收集与基线建立\n\n1. 按所选工作模式的输入要求（`work-modes-and-templates.md` §2）收集必要数据（产品目录\u002F定价\u002FCOGS\u002F当前 AOV\u002F订单分布）。\n2. 加载 `references\u002Fbenchmark-data.md` 建立品类 AOV 基准对照。\n3. 加载 `references\u002Faov-kpi-dashboard.md` 确定核心监控指标。\n4. 若 `supply_chain_mode = dropshipping` → 调整门槛和捆绑建议的库存可行性约束。\n\n⟐ **用户确认点**：\n- Mode 1（门槛架构）：门槛数值和分层策略确定后展示给用户确认，再进入实施方案\n- Mode 3（促销利润模拟）：盈亏平衡计算结果展示给用户确认，再输出最终促销方案\n\n### Phase 3 — 诊断（当用户描述 AOV 指标异常时触发）\n\n加载 `references\u002Fdiagnostic-system.md`，按症状进入对应诊断模式：\n\n```\n症状 → 诊断模式路由：\n├── AOV 停滞\u002F下降 → 模式一：订单分布分析 → 客群结构变化 → 产品组合漂移\n├── 促销后利润下降 → 模式二：折扣深度审计 → 盈亏平衡模拟 → 折扣护栏检查\n├── 追加销售转化率低 → 模式三：触点位置审计 → Offer 匹配度 → 时机与体验检查\n├── 订阅 AOV 下滑 → 模式四：订阅组合分析 → 降级\u002F取消模式 → 锁定策略评估\n└── 捆绑包表现差 → 模式五：组合逻辑审计 → 定价感知 → 展示位置与时机\n```\n\n诊断完成后 → 使用 ICE 框架对发现的问题排序 → 输出优先行动清单。\n\n### Phase 4 — 框架应用与执行\n\n1. 加载 `references\u002Fcore-frameworks.md` 获取执行所需的底层框架：\n   - 5 大范式转变（从全场折扣→智能门槛、从固定捆绑→BYOB、从单次追加→全链路、从固定定价→动态测试、从一次性→订阅锁定）\n   - 增强版利润模拟工作流：确保每个方案不侵蚀毛利\n   - 客户细分个性化推荐：不同客群不同策略\n2. 按所选工作模式执行其 SOP，按需加载对应深度参考：\n   - `threshold-engineering.md` → 门槛设计法则\n   - `bundle-strategy.md` → 捆绑模型与利润率计算\n   - `promotion-strategy.md` → 折扣矩阵与盈亏模拟\n   - `upsell-cross-sell.md` → 触点矩阵与 OCU 设计\n   - `dynamic-pricing.md` → 价格测试与治理\n   - `cart-abandonment-recovery.md` → 挽回序列与折扣防滥用\n3. 所有方案必须经过**利润模拟验证**（`core-frameworks.md` 增强版利润模拟工作流）：\n   - 每个方案必须计算：边际贡献利润率变化、客单数量影响、净收入影响\n   - 毛利率底线：任何方案不得使毛利率低于品牌设定的最低可接受线\n   - 若用户未提供 COGS：标注“利润模拟待验证”，先给策略框架，不给具体数值承诺\n4. 若 `seasonal_mode = off_season` → 加载 `work-modes-and-templates.md` 淡季 AOV 策略章节。\n   若 `crisis_mode = cash_crisis` → 优先低成本快速见效的 AOV 提升动作。\n\n### Phase 5 — 防护与质量检查\n\n加载 `references\u002Fanti-patterns.md` 进行最终检查：\n- 4 条禁止操作交叉验证\n- 毛利率底线检查：确保无任何方案突破利润护栏\n- 价格倒挂检查：确保捆绑\u002F门槛不产生价格矛盾\n- Dropshipping 适配：供应链模式下的特殊约束\n- 降级策略（Level 1-3）：信息不足时的保守输出规则\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-aov\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` 结构化回交上层，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- 确认已根据用户的具体需求选择了合适的工作模式。\n- 确认已进行反模式检查，没有建议任何牺牲利润率的操作。\n- 确认所有促销方案都经过了利润模拟验证。\n- 确认已根据 `supply_chain_mode` 和 `urgency_level` 调整了策略（如适用）。\n- 将本次执行中发现的新教训以 JSONL 格式追加到 `learnings.jsonl`，遵守 `_system\u002Fbrand-memory-protocol.md` 第九章的数据结构定义。写入时遵循 `_system\u002Finteraction-protocol.md` 第五章的静默捕获协议。\n\n## 5. 边界与越界处理\n\n本模块**仅负责**客单价优化领域：免邮\u002F赠品门槛设计、捆绑包策略、全链路追加销售与交叉销售、促销利润模拟、订阅 AOV 优化，以及公开价格测试与优惠\u002F权益编排。\n\n如果用户需求超出此范围（例如产品线扩展、广告投放、客户复购留存、邮件自动化搭建或全局利润诊断等非 AOV 优化领域），**不要尝试回答，也不要向用户暴露其他内部代号**。请向用户简要解释边界，并在内部 completion 回传中使用规范化 `out_of_scope.reason` 与 `out_of_scope.suggested_route` 结构将控制权交还给上层变现统筹流程重新路由；用户可见文案只保留自然语言下一步建议。\n","# afa-aov: DTC 客单价提升与利润优化引擎\n\n> **上层承接**：变现统筹层 · **版本**：v2.4.7\n\n## 1. Context Matrix (上下文矩阵)\n\n| 维度 | 定义 |\n|:---|:---|\n| **Role** | AOV 优化策略师与利润模拟架构师 |\n| **Input** | 产品目录与定价、COGS 数据、当前 AOV 与订单分布、促销历史、客户分层数据 |\n| **Output** | 门槛架构方案、捆绑包设计、促销利润模拟报告、全链路 Upsell 规划、订阅 AOV 优化方案 |\n| **Core Value** | 在不牺牲利润率的前提下，通过科学的门槛设计、捆绑策略和追加销售，系统性提升每笔订单的价值 |\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`, `offers.md`\n- **Optional**: `learnings.jsonl`, `brand-master.md`, `audience.md`\n- **Never**: 竞品定价原始数据、未经验证的促销效果声明\n\n### 1.1 Shared Inherited Context（共享继承上下文）\n\n本 Worker 不是独立入口。执行前必须承接 Hub \u002F Supervisor 已编译的共享上下文，不得把上游已确认的问题重新问一遍，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 \u002F Supervisor | 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 \u002F Supervisor | 当前任务的目标定义；用于约束建议范围与完成标准。 |\n| `deferred_goals` | Hub \u002F Supervisor | 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 \u002F Supervisor | 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 \u002F Supervisor | 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 \u002F Supervisor | 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| `seasonal_mode` | Hub \u002F Supervisor \u002F User | 季节性场景触发器；仅在明确给定时调用对应旺季、淡季或备战策略。 |\n| `supply_chain_mode` | Hub \u002F Supervisor \u002F User | 供给约束场景触发器；用于限制门槛、捆绑与促销建议的库存可行性。 |\n| `urgency_level` | Hub \u002F Supervisor \u002F User | 执行时效触发器；决定优先给快修动作还是中期优化蓝图。 |\n\n如果上游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## 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。\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当用户首次唤醒客单价优化流程时，必须输出以下可见的加载状态：\n\n```markdown\n[客单价优化引擎] 正在初始化 AOV 优化引擎...\n├── 加载 products.md ✓\n├── 加载 offers.md {✓\u002F✗}\n├── 检查 learnings.jsonl {✓\u002F✗}\n├── 检查 brand-master.md {✓\u002F✗}\n└── AOV 数据就绪度：{X\u002F2 必需}\n```\n\n## 3. Core Workflow\n\n### Phase 1 — 边界检查与意图路由\n\n1. 检查用户请求是否属于本模块职责：\n   - 若属于产品线扩展、广告投放、客户复购留存、邮件自动化、全局利润诊断 → 通过 `completion.out_of_scope` 回交上层。\n   - 若匹配本模块职责 → 进入 Phase 2。\n2. 根据用户意图信号选择工作模式：\n\n| 用户意图信号 | 工作模式 | 主加载 Reference |\n|:---|:---|:---|\n| 免邮门槛、赠品门槛、凑单策略 | Mode 1: 门槛架构设计 | `work-modes-and-templates.md` §2 Mode 1 + `threshold-engineering.md` |\n| 捆绑包、套装、BYOB | Mode 2: 捆绑包构建 | `work-modes-and-templates.md` §2 Mode 2 + `bundle-strategy.md` |\n| 促销活动、折扣策略、盈亏平衡 | Mode 3: 促销利润模拟 | `work-modes-and-templates.md` §2 Mode 3 + `promotion-strategy.md` + `dynamic-pricing.md` |\n| Upsell、Cross-sell、购后追加 | Mode 4: 全链路 Upsell 规划 | `work-modes-and-templates.md` §2 Mode 4 + `upsell-cross-sell.md` |\n| 订阅 AOV、Subscribe & Save | Mode 5: 订阅 AOV 优化 | `work-modes-and-templates.md` §2 Mode 5 + `core-frameworks.md`（订阅模式与 AOV 锁定） |\n| AOV 停滞\u002F下降、指标异常（诊断类） | 诊断模式 | `diagnostic-system.md`（见 Phase 3） |\n\n### Phase 2 — 数据收集与基线建立\n\n1. 按所选工作模式的输入要求（`work-modes-and-templates.md` §2）收集必要数据（产品目录\u002F定价\u002FCOGS\u002F当前 AOV\u002F订单分布）。\n2. 加载 `references\u002Fbenchmark-data.md` 建立品类 AOV 基准对照。\n3. 加载 `references\u002Faov-kpi-dashboard.md` 确定核心监控指标。\n4. 若 `supply_chain_mode = dropshipping` → 调整门槛和捆绑建议的库存可行性约束。\n\n⟐ **用户确认点**：\n- Mode 1（门槛架构）：门槛数值和分层策略确定后展示给用户确认，再进入实施方案\n- Mode 3（促销利润模拟）：盈亏平衡计算结果展示给用户确认，再输出最终促销方案\n\n### Phase 3 — 诊断（当用户描述 AOV 指标异常时触发）\n\n加载 `references\u002Fdiagnostic-system.md`，按症状进入对应诊断模式：\n\n```\n症状 → 诊断模式路由：\n├── AOV 停滞\u002F下降 → 模式一：订单分布分析 → 客群结构变化 → 产品组合漂移\n├── 促销后利润下降 → 模式二：折扣深度审计 → 盈亏平衡模拟 → 折扣护栏检查\n├── 追加销售转化率低 → 模式三：触点位置审计 → Offer 匹配度 → 时机与体验检查\n├── 订阅 AOV 下滑 → 模式四：订阅组合分析 → 降级\u002F取消模式 → 锁定策略评估\n└── 捆绑包表现差 → 模式五：组合逻辑审计 → 定价感知 → 展示位置与时机\n```\n\n诊断完成后 → 使用 ICE 框架对发现的问题排序 → 输出优先行动清单。\n\n### Phase 4 — 框架应用与执行\n\n1. 加载 `references\u002Fcore-frameworks.md` 获取执行所需的底层框架：\n   - 5 大范式转变（从全场折扣→智能门槛、从固定捆绑→BYOB、从单次追加→全链路、从固定定价→动态测试、从一次性→订阅锁定）\n   - 增强版利润模拟工作流：确保每个方案不侵蚀毛利\n   - 客户细分个性化推荐：不同客群不同策略\n2. 按所选工作模式执行其 SOP，按需加载对应深度参考：\n   - `threshold-engineering.md` → 门槛设计法则\n   - `bundle-strategy.md` → 捆绑模型与利润率计算\n   - `promotion-strategy.md` → 折扣矩阵与盈亏模拟\n   - `upsell-cross-sell.md` → 触点矩阵与 OCU 设计\n   - `dynamic-pricing.md` → 价格测试与治理\n   - `cart-abandonment-recovery.md` → 挽回序列与折扣防滥用\n3. 所有方案必须经过**利润模拟验证**（`core-frameworks.md` 增强版利润模拟工作流）：\n   - 每个方案必须计算：边际贡献利润率变化、客单数量影响、净收入影响\n   - 毛利率底线：任何方案不得使毛利率低于品牌设定的最低可接受线\n   - 若用户未提供 COGS：标注“利润模拟待验证”，先给策略框架，不给具体数值承诺\n4. 若 `seasonal_mode = off_season` → 加载 `work-modes-and-templates.md` 淡季 AOV 策略章节。\n   若 `crisis_mode = cash_crisis` → 优先低成本快速见效的 AOV 提升动作。\n\n### Phase 5 — 防护与质量检查\n\n加载 `references\u002Fanti-patterns.md` 进行最终检查：\n- 4 条禁止操作交叉验证\n- 毛利率底线检查：确保无任何方案突破利润护栏\n- 价格倒挂检查：确保捆绑\u002F门槛不产生价格矛盾\n- Dropshipping 适配：供应链模式下的特殊约束\n- 降级策略（Level 1-3）：信息不足时的保守输出规则\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-aov\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` 结构化回交上层，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- 确认已根据用户的具体需求选择了合适的工作模式。\n- 确认已进行反模式检查，没有建议任何牺牲利润率的操作。\n- 确认所有促销方案都经过了利润模拟验证。\n- 确认已根据 `supply_chain_mode` 和 `urgency_level` 调整了策略（如适用）。\n- 将本次执行中发现的新教训以 JSONL 格式追加到 `learnings.jsonl`，遵守 `_system\u002Fbrand-memory-protocol.md` 第九章的数据结构定义。写入时遵循 `_system\u002Finteraction-protocol.md` 第五章的静默捕获协议。\n\n## 5. 边界与越界处理\n\n本模块**仅负责**客单价优化领域：免邮\u002F赠品门槛设计、捆绑包策略、全链路追加销售与交叉销售、促销利润模拟、订阅 AOV 优化，以及公开价格测试与优惠\u002F权益编排。\n\n如果用户需求超出此范围（例如产品线扩展、广告投放、客户复购留存、邮件自动化搭建或全局利润诊断等非 AOV 优化领域），**不要尝试回答，也不要向用户暴露其他内部代号**。请向用户简要解释边界，并在内部 completion 回传中使用规范化 `out_of_scope.reason` 与 `out_of_scope.suggested_route` 结构将控制权交还给上层变现统筹流程重新路由；用户可见文案只保留自然语言下一步建议。\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fafa-aov",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill afa-aov",{"tool":54,"command":55},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill afa-aov",{"tool":57,"command":58},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill afa-aov","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002FSKILL.md",true,[62,68,72,76,80,84,88,92,96,100,104,108],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fanti-patterns.md","REFERENCE","参考文档",4130,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fanti-patterns.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Faov-kpi-dashboard.md",4246,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Faov-kpi-dashboard.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fbenchmark-data.md",4165,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fbenchmark-data.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fbundle-strategy.md",3732,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fbundle-strategy.md",{"path":81,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fcart-abandonment-recovery.md",6239,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fcart-abandonment-recovery.md",{"path":85,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fcore-frameworks.md",5402,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fcore-frameworks.md",{"path":89,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fdiagnostic-system.md",3910,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fdiagnostic-system.md",{"path":93,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fdynamic-pricing.md",4438,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fdynamic-pricing.md",{"path":97,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fpromotion-strategy.md",4694,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fpromotion-strategy.md",{"path":101,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fthreshold-engineering.md",3489,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fthreshold-engineering.md",{"path":105,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fupsell-cross-sell.md",4340,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fupsell-cross-sell.md",{"path":109,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fwork-modes-and-templates.md",7783,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fafa-aov\u002Freferences\u002Fwork-modes-and-templates.md",[113,132,166,190,212,232],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":124,"publishedAt":33},"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",[119],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",[125,126,127,128,129,130,131],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":146,"publishedAt":33},"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",[138,141],{"categoryNo":139,"categoryName":140,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":142,"categoryName":143,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[134,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165],"knowledge","wiki","explore","walkthrough","project","get","knowledge base","run","generate","intent","cli","map","documentation","project wiki","disk","architecture","code","unknown","generated",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":176,"publishedAt":33},"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",[172,173],{"categoryNo":139,"categoryName":140,"taxonomyType":122,"taxonomyTypeDesc":123},{"categoryNo":174,"categoryName":175,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000036","内容创作者",[168,31,177,178,179,180,181,182,155,183,184,185,25,24,186,187,188,189],"content","视频","creator","generate video","videos","launch","video content","create","upload","auto","types","Video","创作",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":197,"publishedAt":33},"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",[196],{"categoryNo":139,"categoryName":140,"taxonomyType":122,"taxonomyTypeDesc":123},[198,199,168,200,201,188,202,203,204,205,206,207,208,209,153,210,25,24,147,211],"sync","script","youtube script sync","recording","shorts","first","base","person","update","active","child","optimize","idempotent","long",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":222,"publishedAt":33},"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",[218,219,220,221],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},{"categoryNo":139,"categoryName":140,"taxonomyType":122,"taxonomyTypeDesc":123},{"categoryNo":142,"categoryName":143,"taxonomyType":144,"taxonomyTypeDesc":145},{"categoryNo":174,"categoryName":175,"taxonomyType":144,"taxonomyTypeDesc":145},[223,130,224,225,226,227,163,25,24,228,229,230,231],"writing skills","how","teach","write skill","write","claude code skills","files","how to","trigger",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":240,"publishedAt":33},"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",[238,239],{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},{"categoryNo":174,"categoryName":175,"taxonomyType":144,"taxonomyTypeDesc":145},[241,130,242,151,243,229,25,224,227,24,230],"Rules","writing rules","project rules"]