Update to BuyerTwin

{
  "description": "Use when the user asks to create buyer-facing content or a content brief grounded in canonical BuyerTwin intelligence for one or more target buyers.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 466
    },
    {
      "relative_path": "references/buyer-content-methodology.md",
      "size_in_bytes": 5801
    }
  ],
  "name": "create-buyer-content",
  "skill_md_contents": "---\nname: create-buyer-content\ndescription: Use when the user asks to create buyer-facing content or a content brief grounded in canonical BuyerTwin intelligence for one or more target buyers.\n---\n\nUse this skill when the user asks to create content strategy/briefs or finished content for specific buyers, buyer segments, or all buyers in scope.\n\nDo not use this as the primary workflow for:\n- buyer reaction simulation requests\n- stored buyer comparison requests\n- supplied-message evaluation requests\n- sales-call preparation workflows\n- buyer knowledge mutation\n\nCore workflow:\n1. Resolve buyer scope deterministically.\n2. Establish buyer grounding before drafting: situation, objective movement, relevant tensions, likely questions, objections, proof needs, and useful terminology.\n3. Retrieve only the canonical BuyerTwin intelligence needed for the requested artifact.\n4. Determine whether the user asked for brief mode or finished-content mode.\n5. For multi-buyer requests, identify shared versus buyer-specific intelligence before writing.\n6. Create strategy and/or content grounded in evidence, preserving meaningful differences.\n7. Use ask_buyer selectively only when reaction testing materially improves strategy.\n\nBuyer scope rules:\n- One named buyer means that buyer.\n- Multiple named buyers means all named buyers.\n- Explicit segment/subset means that subset.\n- \"All buyers\" means all accessible buyers in scope.\n- \"My buyers\" without narrowing defaults to all accessible buyers in scope.\n- Do not silently choose a relevance-based subset.\n\nEvidence hierarchy:\n- BuyerTwin Knowledge is authoritative for buyer facts.\n- BuyerTwin Simulation (ask_buyer) is optional and selective.\n- AI Synthesis covers strategy, structure, and generated content.\n- Generated content is not canonical BuyerTwin knowledge.\n- BuyerTwin establishes buyer relevance, buyer context, and buyer perspective; it does not establish factual truth of company, product, competitor, customer, or market claims.\n\nContent guardrails:\n- Do not invent company/product/market facts, proof, statistics, quotes, case-study outcomes, or competitor claims.\n- If evidence is needed but unavailable, request it or use explicit placeholder guidance.\n- Do not start with generic copy and then append persona keywords.\n- Adapt depth to artifact type and message purpose.\n- If buyers are too different for one artifact, recommend variants rather than forcing an artificial average.\n- Do not claim Website Alignment analysis unless exposed MCP tools provide those outputs.\n\nFor detailed buyer-content strategy methodology, consult:\n- references/buyer-content-methodology.md\n"
}