{"id":17719,"plugin_id":"plugins_6a7b24748f9c81919d90e93b7cf0ce51","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:14:19.978Z","digest":"0fd5834f0b93cdf56028a454a883933c8996dc0418b56f0c38b7b910a645530a","against":null,"payload":{"description":"Diagnose ambiguous marketing, growth, revenue, acquisition, retention, brand, channel, or go-to-market problems before recommending tactics. Use when a user asks why sales are not growing, what marketing should prioritize, whether to invest in ads/SEO/SNS/CRM/MA, how to choose among competing initiatives, or needs the business and customer-decision structure decomposed into demand, recall/acquisition, choice/value realization, availability, continuation, and relationship. Identify the maximum bottleneck, evidence gaps, what not to do, and whether a specialist measurement, advertising, B2B, CRM/LTV, communications, or reasoning audit is needed.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":463},{"relative_path":"assets/icon.svg","size_in_bytes":481},{"relative_path":"references/core-principles.md","size_in_bytes":3657},{"relative_path":"references/diagnostic-model.md","size_in_bytes":4705},{"relative_path":"references/output-contract.md","size_in_bytes":2175}],"name":"diagnose-marketing-structure","skill_md_contents":"---\nname: diagnose-marketing-structure\ndescription: \"Diagnose ambiguous marketing, growth, revenue, acquisition, retention, brand, channel, or go-to-market problems before recommending tactics. Use when a user asks why sales are not growing, what marketing should prioritize, whether to invest in ads/SEO/SNS/CRM/MA, how to choose among competing initiatives, or needs the business and customer-decision structure decomposed into demand, recall/acquisition, choice/value realization, availability, continuation, and relationship. Identify the maximum bottleneck, evidence gaps, what not to do, and whether a specialist measurement, advertising, B2B, CRM/LTV, communications, or reasoning audit is needed.\"\n---\n\n# Diagnose Marketing Structure\n\nTreat this skill as the entry point to Marketing Compass. Diagnose the constraint before generating tactics. Do not assume the channel named by the user is the actual problem.\n\nRead [references/core-principles.md](references/core-principles.md) for every substantive diagnosis. Read [references/diagnostic-model.md](references/diagnostic-model.md) when mapping the business, selecting equations, or comparing bottlenecks. Read [references/output-contract.md](references/output-contract.md) before returning a full diagnosis or requesting missing information.\n\n## Establish the decision\n\nIdentify:\n\n- Who must decide what\n- The decision deadline\n- Available budget or capacity\n- Tolerable loss and irreversible risks\n- What is outside the decision scope\n\nIf critical context is missing, ask at most three questions that could change the decision. Do not demand exhaustive discovery. When useful, continue with an explicitly provisional diagnosis.\n\nDo not ask for a metric merely because it is conventionally available. Ask only when it distinguishes competing bottleneck hypotheses.\n\n## Classify the demand problem\n\nDistinguish:\n\n1. **Base demand occurrence:** the need state or event exists independently of marketing.\n2. **Demand recognition:** the customer has the problem but has not recognized or articulated it.\n3. **Demand acceleration:** marketing can bring a future decision forward.\n4. **Context or category creation:** marketing can create a new meaning, use case, or comparison frame, with high uncertainty.\n\nDo not say simply that marketing can or cannot create demand. Name which of the four is in scope.\n\n## Build the smallest useful structure\n\nChoose the model that matches the decision. Do not fill every framework.\n\n- Revenue accounting: trial revenue plus repeat revenue\n- Measurable operating model: traffic × conversion × value × continuation\n- Customer-decision model: demand → recall/acquisition → choice/value realization → continuation/relationship\n- Availability model: mental availability × physical availability\n- B2B model: demand-bearing account → contact/recall → problem resolution and comparison → internal approval → value realization → continuing relationship\n\nSeparate:\n\n- Known values\n- Proxy values\n- Unknown values\n- Meaning equations, accounting equations, probability equations, and hypothesis trees\n\nNever calculate with a meaning equation or an uncalibrated hypothesis tree.\n\n## Select the maximum bottleneck\n\nGenerate competing bottleneck hypotheses, then compare them using:\n\n1. Expected effect on the total outcome\n2. Proximity to zero or a hard constraint\n3. Evidence strength\n4. Ability to influence the variable\n5. Time to learn\n6. Reversibility and downside\n7. Implementation and organizational feasibility\n\nSelect one primary bottleneck and, when needed, one secondary hypothesis. If evidence cannot distinguish them, recommend the smallest test that can.\n\nDo not select a variable merely because it is easiest to measure. Do not list many equal priorities.\n\n## Test the customer decision\n\nCheck only the dimensions relevant to the suspected bottleneck:\n\n- Trigger or need state\n- Recall and consideration set\n- Choice criteria and preference\n- Price, trust, proof, and perceived risk\n- Physical and digital availability\n- Purchase or adoption friction\n- Expectation versus experienced value\n- Re-purchase, re-selection, or continuation\n- For B2B: stakeholders, approval, comparison, budget, urgency, and internal explanation\n\nTreat communications as one possible intervention, not marketing as a whole. Do not use promotion to compensate for absent value, availability, or value realization.\n\n## Determine the evidence status\n\nSeparate facts, interpretations, hypotheses, and unknowns. Assign the evidence level in `core-principles.md`.\n\nCheck for:\n\n- Confounding and reverse causality\n- Selection and survivorship bias\n- Missing attitudinal change because only behavior is logged\n- Averages hiding segments\n- A copied success case with different conditions\n- Stale platform, market, or organizational assumptions\n\nWhen only observational evidence exists, describe consistency or a plausible hypothesis, not causal proof.\n\n## Decide and route\n\nReturn one of:\n\n- Execute\n- Small reversible test\n- Hold pending evidence\n- Reduce or contain\n- Stop or withdraw\n\nRoute to a specialist domain only after stating why:\n\n- Measurement, KPI, MMM, experiments, Signals/Guardrails → marketing measurement\n- Current-value, non-current-value, structural advertising → advertising investment\n- ICP, deals, meetings, internal approval, downloaded materials → B2B growth\n- MA readiness, strategic/operational CRM, CS, LTV → MA/CRM/LTV\n- Recall, meaning, PESO, expectations, touchpoint roles, buzz → marketing communications\n- Causal claims, data quality, stale assumptions, organizational self-sabotage → marketing reasoning audit\n\nIf no specialist skill is available, still state the needed specialist analysis rather than fabricating it.\n\n## Return a decision, not a framework dump\n\nUse the compact output in [references/output-contract.md](references/output-contract.md). Include:\n\n- The core diagnosis first\n- Primary bottleneck and competing hypothesis\n- Evidence and uncertainty\n- Next action and what not to do\n- Signal, counter-signal, guardrail, and review point when a real decision is being made\n\nAdapt depth to the request. Do not force every field into a simple answer.\n\n## Guardrails\n\n- Do not attribute revenue change to one tactic without a defensible counterfactual.\n- Do not invent numbers to complete a model.\n- Do not call a proxy the underlying construct.\n- Do not recommend large execution before locating the bottleneck.\n- Do not treat a weak signal such as a content download as purchase intent.\n- Do not use MA or CRM to replace demand, ICP, value, or competitive advantage.\n- Do not optimize an irreversible threshold problem as if it were a smooth response curve.\n- Do not confuse a logically elegant plan with one that the operating organization can execute.\n- Do not present Marketing Compass classifications as universal industry terminology.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}