Update to PrePilot Lite

{
  "description": "Use when the user wants to understand customers, buyers, users, pains, triggers, objections, Jobs-to-Be-Done, buying language, or patterns in interviews, reviews, calls, communities, surveys, and support data.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 239
    }
  ],
  "name": "customer-research",
  "skill_md_contents": "---\nname: customer-research\ndescription: Use when the user wants to understand customers, buyers, users, pains, triggers, objections, Jobs-to-Be-Done, buying language, or patterns in interviews, reviews, calls, communities, surveys, and support data.\n---\n\n# Customer Research\n\n## Use it for\n\n- Synthesizing interviews, reviews, sales calls, support tickets, or survey responses\n- Planning desk research when first-party research is missing\n- Building JTBD, objection, trigger, and language insights\n- Preparing inputs for positioning or copy\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- Keep direct evidence separate from interpretation.\n- Do not fabricate quotes or frequency counts.\n- Frequency is not enough: capture intensity, business impact, and buying relevance.\n- If desk research is used, identify source type and recency.\n\n## Workflow\n\n1. Choose mode: synthesize supplied evidence or research public sources.\n2. Extract situation, trigger, desired progress, current workaround, pain, consequence, objection, proof requirement, and exact language.\n3. Cluster recurring patterns without erasing meaningful minority segments.\n4. Rank themes by decision relevance using frequency, intensity, and commercial impact.\n5. Translate findings into messaging implications, product questions, and research gaps.\n\n## Output contract\n\n- Top themes with evidence\n- JTBD and trigger statements\n- Objection and proof matrix\n- Customer-language bank\n- Research gaps and recommended next interviews or sources\n\n## Quality gate\n\n- Quotes remain exact when quoted\n- No invented percentages\n- Interpretations are labeled\n- Findings change a marketing decision, not just describe the audience\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"
}