{"id":50312,"plugin_id":"plugin_asdk_app_6ac0205fa0b88191ad16b5a828ce8ce2","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T13:42:46.269Z","digest":"4f054baf10ef9741dc296b2a622be7650968b4431aa03acf48eea0c39e8c4d74","against":null,"payload":{"description":"Use when the user wants to know how one or more target buyers are likely to think, react, question, prioritize, object to, or respond to something, grounded in BuyerTwin intelligence.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":412},{"relative_path":"references/methodology.md","size_in_bytes":4800}],"name":"ask-buyers","skill_md_contents":"---\nname: ask-buyers\ndescription: Use when the user wants to know how one or more target buyers are likely to think, react, question, prioritize, object to, or respond to something, grounded in BuyerTwin intelligence.\n---\n\nUse this skill when the user asks for buyer perspective simulation, such as what one or more buyers would think, feel, say, question, object to, prioritize, believe, doubt, or how they would react.\n\nDo not use this as the primary workflow for:\n- pure stored-intelligence comparison\n- content creation\n- sales-preparation workflow generation\n- buyer knowledge mutation\n\nCore workflow:\n1. Resolve buyers using BuyerTwin tools before simulation.\n2. Use ask_buyer as the simulation mechanism.\n3. For multiple buyers, call ask_buyer separately for each buyer.\n4. Retrieve additional canonical BuyerTwin intelligence only when it directly answers the question or materially improves grounding.\n5. Synthesize only after per-buyer responses exist.\n6. Surface agreement, disagreement, and outliers without forcing consensus.\n\nCanonical-first routing:\n- If the request is directly answerable from canonical BuyerTwin knowledge, answer canonically instead of generating unnecessary simulation.\n- Use simulation primarily for reaction, perspective, and \"what would they think\" questions.\n\nBuyer resolution rules:\n- Never invent buyers.\n- If the user names one buyer, resolve that buyer.\n- If the user names several buyers, resolve all named buyers.\n- If the user specifies a segment or other explicit subset, use that subset.\n- If the user explicitly asks for \"all buyers,\" use all accessible buyers in the applicable workspace/scope.\n- If the user says \"my buyers\" without further narrowing, default to all accessible buyers in scope.\n- Do not silently select a subset based on model-defined relevance.\n- Do not silently omit a buyer because a response seems redundant.\n- If technical limits prevent using the entire requested set, disclose that limitation.\n- If a buyer reference is ambiguous and cannot be resolved, ask a clarifying question instead of guessing.\n\nEvidence discipline:\n- Keep BuyerTwin Knowledge (retrieved canonical data), BuyerTwin Simulation (ask_buyer outputs), and AI Synthesis (assistant conclusions) distinct.\n- Canonical BuyerTwin Knowledge has factual authority over BuyerTwin Simulation.\n- If canonical knowledge and simulation conflict, use canonical knowledge for factual claims, treat simulation as contextual reasoning, and surface material inconsistencies.\n- Do not present simulated output as literal statements from real customers/prospects.\n- Do not present synthesis as stored BuyerTwin fact.\n- Prefer probabilistic language for simulation (for example: likely, may, would probably, appears likely, simulation suggests).\n- First-person buyer voice is allowed only when explicitly requested (for example, \"answer as the buyer\") and must still be identified as simulated.\n\nGuardrails:\n- Do not collapse multi-buyer requests to one buyer.\n- Do not hide meaningful disagreement.\n- Do not convert a majority view into universal consensus.\n- Do not use propose_buyer_knowledge_update or apply_buyer_knowledge_update.\n- Do not claim website/page Alignment, Pull/Hold, or belief/trust/clarity/risk scoring unless exposed MCP tools actually provide those outputs.\n\nFor detailed BuyerTwin methodology, boundary handling, and synthesis rules, consult:\n- references/methodology.md\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}