Update to PrePilot Lite

{
  "description": "Use when the user needs a marketing direction, annual or quarterly plan, channel priorities, growth thesis, budget logic, objectives, funnel choices, or a strategy that connects market evidence to execution.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 232
    }
  ],
  "name": "marketing-strategy",
  "skill_md_contents": "---\nname: marketing-strategy\ndescription: Use when the user needs a marketing direction, annual or quarterly plan, channel priorities, growth thesis, budget logic, objectives, funnel choices, or a strategy that connects market evidence to execution.\n---\n\n# Marketing Strategy\n\n## Use it for\n\n- Annual or quarterly planning\n- Client strategy\n- Channel prioritization\n- Budget and resource tradeoffs\n- Turning diagnosis into a coherent set of marketing choices\n\n## Operating rules\n\n- Use context already present in the conversation before asking for more input.\n- Separate known facts, reasonable assumptions, and unknowns. Do not present assumptions as evidence.\n- When the answer depends on current platform rules, market conditions, pricing, benchmarks, or competitors, verify them with current sources when tools are available.\n- Prefer concrete decisions, examples, and next actions over generic marketing advice.\n- Do not invent campaign performance, customer quotes, research findings, testimonials, rankings, or competitor claims.\n- Keep the requested market, language, funnel stage, audience awareness, budget, and channel constraints visible throughout the work.\n- Strategy means choices and exclusions, not a list of tactics.\n- Tie recommendations to the business model, audience, stage, budget, and evidence.\n- Do not estimate outcomes with false precision.\n- Separate strategic bets from operating hygiene.\n\n## Workflow\n\n1. Define business objective, economic constraint, time horizon, and current baseline.\n2. Diagnose audience demand, offer strength, competitive context, funnel constraints, and measurement quality.\n3. Choose priority segments, message, acquisition motions, and retention/growth motions.\n4. Define the few strategic bets that can change the outcome.\n5. Assign channels by role in the buying process, not popularity.\n6. Set KPI tree, leading indicators, review cadence, and stop/continue rules.\n7. Create a phased action plan with owners or resource needs where known.\n\n## Output contract\n\n- Strategy on a page\n- Priority bets and explicit non-priorities\n- Channel role matrix\n- KPI tree and review cadence\n- 30/60/90-day action plan or requested horizon\n\n## Quality gate\n\n- Every tactic serves a stated strategic choice\n- Budget logic is explained\n- KPIs map to business outcomes\n- The plan can survive removal of fashionable channels\n\n## Opportunity sizing and focus\n\nWhen the strategic decision depends on market size or where to enter first:\n\n1. Define the market boundary before calculating anything: problem, customer type, geography, use case, and buying unit.\n2. Triangulate opportunity size with at least two independent methods when data permits, such as a category-level estimate and a customer-count × spend model.\n3. Label sourced inputs, modeled inputs, assumptions, and confidence separately. Do not turn uncertain assumptions into precise forecasts.\n4. Narrow the initial focus by comparing segment pain, ability and willingness to buy, access/distribution, competitive winnability, reference value, and strategic fit.\n5. Prefer a focused entry segment when resources are limited, but never invent an arbitrary market-share target as proof that the segment is \"winnable.\"\n\n## Strategy stress test\n\nFor high-stakes plans, identify the 3 to 5 assumptions that would invalidate the strategy if false. For each, state the failure condition, evidence that could be collected cheaply, a decision threshold, and the smallest useful test. Give credit to assumptions that already have strong evidence instead of manufacturing doubt.\n\n## Handoff\n\nIf the task is part of a larger marketing request, return the completed deliverable plus the evidence or decisions the next PrePilot skill needs. Do not repeat upstream analysis unless it changes the result.\n"
}