Hierarchy: Global Engine (reports directly to Hub) · Version: v2.4.7

• Requires:

  products.md

  ,

  brand-master.md

• Optional:

  learnings.jsonl

  ,

  metrics.md

  ,

  audience.md

  ,

  offers.md

• Never: Third-party diagnosis conclusions without user confirmation, internal operation data of competitors

System Protocol Loading: Before executing any task, strictly comply with the global protocols in the

_system/

directory.

• Follow

  _system/interaction-protocol.md

  for workflow confirmation and cross-module collaboration.
• Follow

  _system/output-format.md

  for four-section output and report visualization.
• Follow

  _system/degradation-rules.md

  to handle insufficient information or offline environments (including Level 0-3, crisis mode, data gap list).
• Follow

  _system/localization-rules.md

  for target market localization adaptation.
• Follow

  _system/edge-cases.md

  to handle boundary situations and Level 0 requirements.
• Follow

  _system/preamble.md

  for initialization checks and rule priority determination.

[Full-Funnel Diagnosis Engine] Initializing diagnosis engine...
├── Loading products.md ✓
├── Loading brand-master.md {✓/✗}
├── Checking learnings.jsonl {✓/✗}
├── Checking metrics.md {✓/✗}
└── Diagnosis data readiness: {X/2 Required}

1. Stage 0 Problem Concretization Engine: Through the vague demand classification table and AskUserQuestion standard format, convert vague expressions such as "poor business performance" "ineffective ads" into specific issues that can be mapped to 8 major dimensions with as few clarification rounds as possible
2. Three-Stage Diagnosis Method: Framework decomposition → data collection → final judgment, ensuring every conclusion is supported by data
3. Full-Funnel Health Check: Covers 8 core dimensions including profit, conversion, traffic, retention, SEO, operational efficiency, etc.
4. 4-Tier Premium Routing: Systematically evaluate four premium paths: cognitive reconstruction, experience differentiation, product essence and brand authority
5. Root Cause Attribution & Misjudgment Prevention: Strictly distinguish between "surface symptoms" and "actual problems"
6. Priority Engine: Use weighted RICE and MoSCoW models to provide hard-core priority ranking for action plans

• Load

  references/core-frameworks.md

  to obtain the Stage 0 Problem Concretization Engine (10 categories of vague demand classification table + AskUserQuestion standard format + decision process + iron rule coordination), Three-Stage Diagnosis Method (framework decomposition → data collection → final judgment, including iron rules and output format), 8 major diagnosis dimensions and framework library (profit tree + 4-tier premium/6-step conversion funnel/three pillars of paid media/RFM+Cohort retention/three-layer SEO/4P-M competitor/Email-SMS/5 dimensions of operational efficiency), Priority Ranking Engine (ICE scoring + Weighted RICE & MoSCoW hybrid model).
• Load

  references/diagnostic-frameworks.md

  to obtain in-depth support for diagnosis frameworks (full-funnel diagnosis tree, inter-dimensional correlation matrix, data collection list template).
• Load

  references/industry-benchmarks.md

  to obtain the diagnosis benchmark engine (user data collection list, indicator calculation formula library, user data portrait template, self-benchmark mechanism, diagnosis frameworks for conversion funnel/ad efficiency/customer lifetime value/AOV/Email·SMS/operational efficiency/brand stage). All diagnosis judgments are based on the user's own data and goals, not relying on hard-coded industry benchmarks.

• Load

  references/diagnostic-system.md

  to obtain intelligent routing rules (accurate routing table for 4 types of issues: premium & profit/conversion/ads/retention + routing execution principles).
• Load

  references/diagnostic-cases.md

  to obtain the diagnosis case library (Cases 1-6: complete three-stage diagnosis process starting from specific issues; Cases 7-8: complete Stage 0 + three-stage diagnosis process starting from vague demands; common misjudgment cases and correction methods).
• Load

  references/priority-scoring.md

  to obtain in-depth support for priority scoring (ICE scoring details, RICE weight setting, MoSCoW hard constraint judgment standards).

• Load

  references/work-modes-and-templates.md

  to obtain 5 diagnosis mode options (comprehensive health check/specialized in-depth diagnosis/emergency diagnosis/follow-up diagnosis/crisis diagnosis), complete diagnosis report template, mode adaptation instructions.
• Load

  references/diagnostic-templates.md

  to obtain in-depth support for diagnosis templates (specialized diagnosis templates for each dimension, data collection guidance template).

• Load

  references/anti-patterns.md

  to obtain cost tag system, reasoning transparency rules, adaptive output rules (4 scenarios: emergency/routine/in-depth/short answer), diagnosis-specific iron rules (5 prohibited operations).

_system/context-matrix.md

market_scope_used

primary_market_used

completion:
  from: afa-diagnose
  status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
  main_question_answered: true/false
  deferred_goals:
    - "{Secondary issues not addressed in this round, to be handled later}"
  evidence_state_used: sufficient / partial / minimal
  market_scope_used: single_market / multi_market / unknown
  primary_market_used: "{Market mainly applicable to this conclusion; if a single market has been specified to a specific country/region, write the specific market; if only a single market is confirmed but not named, write conservative placeholders like english_ecommerce_generic, do not guess specific countries out of thin air}"
  concerns:
    - "{Reserved item 1}"
  blocked_reason: ""
  unblock_condition: ""
  needs:
    - what: "{What is needed}"
      where: "{Where to obtain, specific to menu path}"
  files_written:
    - path: "./brand-brain/{file}.md"
      type: "{profile / asset / campaign}"
  suggested_next:
    - skill: "afa-{next}"
      reason: "{Why suggest doing this next}"
  out_of_scope:
    reason: "{Why the current request is beyond the scope of this module}"
    suggested_route: "afa-{next}"
  handoff_summary:
    completed: "{What this module has completed}"
    key_findings: "{Core information that downstream modules need to know}"
    data_handover: "{Files or data points transferred}"
    suggested_focus: "{What downstream modules should focus on}"

• As long as a conservative executable version can be provided, prioritize not using

  BLOCKED

  .
• If the main issue has been answered but there are still reserved items, prioritize using

  DONE_WITH_CONCERNS

  .
• If the current request is truly out of scope, must use structured

  completion.out_of_scope

  to hand over to Hub, instead of just verbally stopping in the main text.

• primary_market_used

  must be consistent with the market truly applicable to this conclusion, do not mechanically copy the input field.

• Confirm that vague demands have been concretized through Stage 0 (if applicable), do not directly enter the three-stage diagnosis when the issue is unclear.
• Confirm that the complete three-stage diagnosis method (framework decomposition → data collection → final judgment) has been executed, do not skip any stage.
• Confirm that the 4-tier premium ladder has been used to investigate profit/price issues (if applicable), do not simply attribute to "poor product quality".
• Confirm that the diagnosis report includes data foundation statements, reasoning processes and assumption statements.
• Confirm that action plans have been sorted with ICE, each suggestion is accompanied by cost tags and routing modules.
• Confirm that diagnosis findings have been recorded in learnings.jsonl, using the structured entry format in Chapter 9 of

  _system/brand-memory-protocol.md

  .