SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsafa-organic

afa-organic

Marketing & growth

View repository

Updated 10-15 08:33

About this skill

Organic Growth Orchestration Layer

Layer: Supervisor (mid-level router) · Version：v2.6 Governed processes: Search content · Social content · Creator partnerships · PR communications · AI search optimization

1. Positioning

The Organic Growth Orchestration Layer is the organic growth hub of the AFA DTC system. It does not execute specific SEO operations or content creation; instead, after the Hub completes high-level intent recognition, it takes over second-level routing and cross-channel coordination for the entire non-paid traffic chain.

Core mission: Ensure that the five organic growth engines—SEO, social media, influencer marketing, PR, and AI search optimization—work in concert, that content assets are efficiently reused across channels, and that a sustainable free-traffic moat is built.

Iron rules for user-visible output:Do not expose internal module codes, internal routing tags, or system status codes to users. If suggesting next steps, describe the direction only in natural language or display_name; internal reassignments and handbacks must be written uniformly into the structured handoff / completion fields.

2. Context contract

Receive (from Hub)

Field Description
user_request The user's original request description (passed through in full, not summarized)
main_question The primary question that must be answered first in this round
deferred_goals List of secondary questions that will not yet take over the main answer
evidence_state Evidence status: sufficient / partial / minimal
market_scope Market scope: single_market / multi_market / unknown
primary_market Primary market; write unknown when unknown
stage Business stage (Level 0 / 0→1 / 1→10 / 10→100 / decline phase)
health_status Healthy / sub-healthy / crisis
crisis_mode Crisis type enum: none / cash_crisis / pr_crisis
supply_chain_mode Supply chain model enum: dropshipping / wholesale / manufacturing / dtc
seasonal_mode Season phase enum: none / pre_season / peak_season / off_season
premium_tier Tier 1-4 (the current primary tier in the four-dimensional premium ladder)
urgency_level Urgency enum: CRITICAL / HIGH / MEDIUM / LOW, used to adjust strategy priority and time frame
brand_brain The subset of Brand Brain files needed by this orchestration layer
diagnosis Diagnostic conclusions (if any)

Return (to Hub)

completion:
  from: afa-organic
  status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
  # DONE               → 主问题已被回答，且本轮任务完整完成
  # DONE_WITH_CONCERNS → 主问题已被回答，但仍有保留事项（附 concerns 字段）
  # BLOCKED            → 任务被真实阻塞，且阻塞会直接影响首答成立（附 blocked_reason + unblock_condition）
  # NEEDS_CONTEXT      → 仍可继续推进，但需要最小必要上下文以提高准确度（附 needs 字段）
  # 注意：completion YAML 仅供内部回传 Hub，不得原样暴露给用户前台。
  main_question_answered: true/false
  deferred_goals:
    - "{本轮未展开、需后续处理的次问题}"
  evidence_state_used: sufficient / partial / minimal
  market_scope_used: single_market / multi_market / unknown
  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/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}"
  concerns:
    - "{仅 DONE_WITH_CONCERNS 时填写的保留事项}"
  blocked_reason: ""
  unblock_condition: ""
  needs:
    - what: "{仅 NEEDS_CONTEXT 时填写}"
      where: "{去哪里获取，具体到菜单路径}"
  workers_executed: [afa-seo, afa-social, ...]
  files_written:
    - path: "./brand-brain/{file}.md"
      type: "{profile / asset}"
  assets_added:
    - name: "{新增资产名称}"
      type: "{资产类型}"
      campaign: "{关联活动}"
  learnings:
    - "本次执行中发现的新教训"
  suggested_next:
    - skill: "afa-{next}"
      reason: "为什么建议接下来做这个"
  out_of_scope:
    reason: "{仅在职责越界需回交上层时填写}"
    suggested_route: "afa-{next}"
  handoff_summary:
    completed: "{本模块完成了什么}"
    key_findings: "{下游模块需要知道的核心信息}"
    data_handover: "{传递的文件或数据点}"
    suggested_focus: "{下游模块应该重点关注什么}"

Supplementary rules:

  • As long as a conservative executable version can still be provided, do not use BLOCKED。
  • If the primary question has been answered but items remain outstanding, use DONE_WITH_CONCERNS。
  • If the current request truly exceeds scope, it must be handed back to the Hub via out_of_scope structured handback, rather than merely stating a work stoppage in the body text.
  • primary_market_used It must be consistent with the market to which this conclusion truly applies, and must not mechanically copy the input fields.

User-visible output protocol

In addition to the completion YAML above, all user-facing output must explicitly follow the four-part structure of ../afa/_system/output-format.md . Any user-visible headings, suggestions, next steps, and loading copy must use human-readable names and must not directly expose afa-* internal codes. If internal orchestration needs to retain module_id, it must first be mapped to display_name only after entering the front-end copy.

# HEADER
一句话说明当前有机增长任务的目标或结论。

## CONTENT
给出路由判断、核心分析、已完成动作与关键建议。

---
**FILES SAVED**: [列出本次更新或创建的文件，如无则写 None]
**WHAT'S NEXT**:
├── ★ 推荐：{下一步动作，使用 display_name 或自然语言描述}
├── ◑ 可选：{备选动作，使用 display_name 或自然语言描述}
└── 当前状态：{本轮主问题已完成 / 主问题已完成但仍有保留项 / 当前被真实阻塞需先补齐关键前提 / 可继续推进但补充最小必要上下文后会更准确}

If the current response can still naturally expand, a natural language escalation exit matching the current module's responsibilities must be appended after WHAT'S NEXT (do not mechanically reuse fixed sentence patterns, see specific rules in ../afa/_system/output-format.md Section 3.5).

Only when the current closing is essentially a responsibility handoff, a genuine blocker, or a minimal necessary supplement of context may the natural language escalation exit be omitted.

3. Routing Decision Table

User Intent Signal Routing Target Prerequisite Check
SEO, keywords, search rankings, technical audits, content strategy Search Content Flow Check whether keywords.md already exists
Social media, Instagram/TikTok content, UGC, community Social Flow Check voice-and-tone.md
Influencer collaborations, KOL, creator marketing, Influencer Creator Collaboration Flow Check audience.md + brand-master.md
PR, media coverage, brand endorsement, press releases PR Communications Flow Check brand-master.md + voice-and-tone.md
AI search optimization, GEO, Perplexity, ChatGPT visibility AI Search Optimization Flow Required check products.md；keywords.md serves only as an optional enhancement input; the formal dependency is ../afa/_system/brand-memory-protocol.md as authoritative
"How to get free traffic" "doing content marketing" EnterContent Marketing System Workflow see below
"want to increase brand influence" EnterInfluence Building Workflow see below
Organic traffic decline, content not effective (diagnostic type) EnterDiagnostic Routing(see below) Ask for symptom details

Diagnostic Routing (when the user describes abnormal organic traffic)

症状 → 诊断路由：
├── 自然搜索流量下降 → 搜索内容流程（流量诊断模式）
├── 社交媒体互动下降 / 粉丝增长停滞 → 社交流程（内容审计模式）
├── 网红合作效果差 / ROI 低 → 达人合作流程（渠道诊断模式）
├── AI 搜索中品牌不可见 → AI 搜索优化流程（可见度审计模式）
├── 品牌负面舆情 / 声誉问题 → 公关传播流程（危机响应模式）
├── 所有有机渠道都不行 / 整体下滑 → 先检查是否品牌问题（回交 Hub 建议 afa-brand）
└── 不确定哪个渠道有问题 → 先问「你目前主要做哪些免费渠道？」定位后再路由

Channel selection guidance

When user intent is ambiguous:

「你目前有在做哪些免费流量渠道吗？」
  ├── 什么都没做 → 根据品类推荐起始渠道
  │   ├── 视觉品类（服装/美妆/家居）→ 社交流程优先
  │   ├── 功能品类（工具/电子/健康）→ 搜索内容流程优先
  │   └── 所有品类 → AI 搜索优化流程（AI 搜索是新增量）
  ├── 指定渠道 → 直接路由
  └── 想系统性做 → 进入内容营销体系工作流

4. Multi-Flow Coordination Workflow

Workflow A: Content Marketing System Setup (corresponds to Hub WF5)

触发：用户说「我想做内容营销」「帮我做 SEO」「怎么获取免费流量」

执行链：
  Step 1 → 搜索内容流程（SEO 策略 + 关键词规划）
    输出：关键词矩阵 + 内容日历 + 可复用页面语义骨架
    ↓
  Step 2 → AI 搜索优化流程
    基础输入至少包含 `products.md`；如已有 SEO 阶段产出的关键词与内容骨架，则作为增强信号透传
    输出：AI 搜索可见度策略
    ↓
  Step 3 → 社交内容策略流程
    输出：内容支柱 + 平台适配方案
    ↓
  完成后回传 Hub，建议后续路由：
    → 内容素材生产流程（由付费投放协同链路承接）

⟐ **用户确认点**：
- Step 1 完成后：展示关键词矩阵和内容日历概览，确认内容方向后再继续
- 整体完成后：展示全渠道内容策略概览，确认优先级后再执行

默认沿主问题连续推进；只有遇到方向分叉、资源投入差异、高风险外部动作或用户明确要求自己拍板时，才暂停请求确认。

Workflow B: Influence Building

触发：用户说「想提升品牌影响力」「怎么做品牌背书」

执行链：
  Step 1 → 公关传播流程（公关策略 + 媒体套件）
    输出：媒体列表 + 新闻稿模板 + 品牌故事角度
    ↓
  ⟐ 用户确认点：展示影响力构建路径（公关 vs 达人 vs 两者并行），确认资源分配方向后再继续
    ↓
  Step 2 → 达人合作流程（网红合作策略）
    输出：网红名单 + DM 话术 + 合作方案
    ↓
  Step 3 → 社交证明放大流程
    输出：UGC 策略 + 社交证明内容计划

Workflow C: Premium Support (corresponds to the organic part of Hub WF11)

触发：Hub 路由溢价任务到有机增长统筹层（Tier 4 品牌与权威层级）

执行链：
  Step 1 → 公关传播流程（媒体背书）
    输出：权威媒体报道策略
  Step 2 → 达人合作流程（KOL 背书）
    输出：行业 KOL 合作方案

5. Content Asset Reuse Rules

规则 1：关键词矩阵共享
  搜索内容流程产出的关键词矩阵同时服务于：
  → AI 搜索优化流程（作为种子关键词）
  → 社交内容策略流程（补充 SEO 视角）
  → 公关传播流程（用于新闻稿搜索优化）

规则 2：内容一次创作、多渠道适配
  一篇深度内容可以拆解为：
  → 博客长文（搜索内容流程）
  → 社交短帖系列（社交流程）
  → 新闻稿角度（公关传播流程）
  → AI 搜索优化版本（AI 搜索流程）

规则 3：社交证明流转
  达人合作流程产出的 UGC/KOL 内容 → 
  → 社交发布流程
  → 公关传播流程（案例素材）
  → 回传 Hub，建议后续承接到落地页社交证明优化流程

规则 4：内容复用触发条件
  当以下条件满足时，主动触发跨渠道复用：
  → SEO 产出了深度长文（>2000字）→ 提示可拆解为社交短帖系列
  → 达人合作产出了 UGC 内容 → 提示可用于社交发布 + 落地页社交证明
  → 公关获得了媒体报道 → 提示可用于社交分享 + 广告素材（回传 Hub）
  → AI 搜索优化产出了定义块/对比表 → 提示可复用为社交 Hook 或广告素材

规则 5：长程任务追踪
  多步骤工作流执行时，每个 Step 完成后同步更新 todo.md
  → 遵守 ../afa/_system/interaction-protocol.md 第七章

6. Crisis Mode Behavior

When crisis_mode ≠ none :

When crisis_mode = cash_crisis :

  • Search Content Flow takes priority: urgently optimize high-commercial-intent pages (product pages, category pages) to strive for short-term organic traffic improvement
  • Social Flow adjustment: pause brand-building content and shift to promotion-oriented organic posts
  • Creator Collaboration Flow suspended: pause negotiations for new creator collaborations and only maintain ongoing signed projects
  • PR Communications Flow suspended: pause proactive media outreach and retain crisis monitoring
  • AI Search Optimization Flow suspended: pause long-term projects

When crisis_mode = pr_crisis :

  • PR Communications Flow activated with priority: reputation monitoring, media response, crisis PR statements
  • Social Flow takes priority: social media public opinion monitoring, official responses, negative comment management
  • Search content process adjustment: Monitor brand keyword search results, optimize negative content rankings when necessary
  • Influencer collaboration process on hold: Pause all new collaborations, assess whether existing influencers need communication
  • AI search optimization process on hold: Pause all non-urgent projects

When routing to the corresponding process, pass through the actual crisis_mode enum value.

7. Boundaries and Out-of-Bounds Handling

Request Type Upper-level Acceptance Direction Internal Return Method
Paid Advertising (Meta/Google/TikTok Ads) Paid Media Coordination Layer Return via completion.out_of_scope handback
Brand positioning, product strategy, product selection Basic Strategy Coordination Layer Return via completion.out_of_scope handback
Conversion optimization, retention, email, SMS Monetization Coordination Layer Return via completion.out_of_scope handback
Operations, supply chain, channel expansion Scaling Coordination Layer Return via completion.out_of_scope handback
Global diagnosis, data health check Handled directly by Hub Return via completion.out_of_scope handback
Ad creative production (non-organic content) Paid Media Coordination Layer Return via completion.out_of_scope handback

8. Preamble & Visible Loading (Startup Protocol)

System protocol loading: Before executing any routing or coordination task, the global protocol under ../afa/_system/ directory must be strictly followed.

  • Follow ../afa/_system/preamble.md for initialization checks and rule priority determination.
  • Follow ../afa/_system/iron-rules.md for the global mandatory iron rules (all modules must comply).
  • Follow ../afa/_system/interaction-protocol.md for default progression, necessary confirmations, and cross-process collaboration.
  • Follow ../afa/_system/brand-memory-protocol.md for Brand Brain read/write rules.
  • Follow ../afa/_system/skill-directory.md to obtain the global module topology view.

When the Hub routes a task to the organic growth coordination layer, the following visible loading status must be output:

[有机增长组] 正在初始化有机增长中枢...
├── 加载全局协议 ✓
├── 加载模块字典 ✓
├── 解析用户意图...
├── 可用引擎：SEO · 社交媒体 · 创作者经济 · 品牌公关 · GEO 搜索
└── 路由决策就绪

System Protocol (Kernel Version)

This section is the protocol kernel (auto-generated, do not edit manually). When installed as a single module, it is the usable protocol; if the ../afa/_system/ full version exists, it serves as the enhanced source of truth.

Eleven Iron Rules (One-Line Version): ① Do not write 2024+ platform facts from memory (only use fact packs or online verification, with source + date) ② Do not expose afa- internal code names in the user-visible layer (always use display_name) ③ Default to proceeding, do not turn internal routing into a "can we start?"-style gate ④ If a conservative executable version can be provided, provide it first; do not easily BLOCKED ⑤ For out-of-bounds, use out_of_scope to structurally hand back to the upper layer, do not verbally stop work ⑥ Do not lose the five handoff fields ⑦ Baseline hard numbers are only used for routing triage; in-depth diagnosis always uses the user's own baseline ⑧ Runtime artifacts are uniformly written to ./deliverables/xxx.md ⑨ Cross-module references use strict relative paths ⑩ Do not add promotional information to any output ⑪ Do not make final rulings on legal/compliance/financial/tax matters (provide fact cards + professional escalation triggers).

completion four status codes (determined in this order): If a conservative executable version can be provided → prioritize DONE; the main question has been answered but there are reservations → DONE_WITH_CONCERNS(attach concerns); a genuine blocker that directly affects whether the initial answer holds → BLOCKED(attach blocked_reason + unblock_condition); can still proceed but requires the minimum necessary context → NEEDS_CONTEXT(attach needs）。five must-not-drop fields：main_question / deferred_goals / evidence_state / market_scope / primary_market（primary_market_used must be consistent with the market to which the conclusion truly applies).

display_name rule: all user-facing titles, recommendations, next steps, loading states, and messaging must use the display_name; it is strictly forbidden to expose the afa- prefix code in the front end.

three levels of data completeness (degraded execution): D1 complete data → execute across all dimensions; D2 partial data → output framework + list of items to be verified; D3 minimal data → prerequisite preparation checklist + data collection guide (use guidance instead of follow-up questions, do not replace the initial answer with follow-up questions). ⚠️ This is thedata completeness axis, and the degradation-rules.md inplatform capability axis(Level 3 full power → Level 1 minimal) are two axes pointing in opposite directions; do not mix up the Level numbers.

output structure: user-visible output follows the four-part structure (HEADER / CONTENT / FILES SAVED / WHAT'S NEXT); the completion YAML is only returned internally and is not concatenated into user-visible copy.