Update to PrePilot Lite

{
  "description": "Use when the user wants behavioral science, decision psychology, mental models, persuasion analysis, friction diagnosis, choice architecture, trust, motivation, or habit principles applied to a marketing problem.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 243
    }
  ],
  "name": "marketing-psychology",
  "skill_md_contents": "---\nname: marketing-psychology\ndescription: Use when the user wants behavioral science, decision psychology, mental models, persuasion analysis, friction diagnosis, choice architecture, trust, motivation, or habit principles applied to a marketing problem.\n---\n\n# Marketing Psychology\n\n## Use it for\n\n- Diagnosing why people hesitate or drop off\n- Improving message, offer, pricing, CRO, onboarding, or retention decisions\n- Designing ethical choice architecture\n- Explaining a behavioral pattern in customer behavior\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- Use behavioral concepts as hypotheses, not magic laws.\n- Explain the mechanism and the expected behavior change.\n- Avoid dark patterns, deception, coercion, false scarcity, or manipulative defaults.\n- Prefer a small number of relevant principles over a long list of biases.\n\n## Workflow\n\n1. Define the target behavior and current behavior.\n2. Identify the main motivational, cognitive, trust, or friction barrier.\n3. Select one to three relevant behavioral principles.\n4. Translate each principle into a specific intervention.\n5. Define what evidence would support or reject the hypothesis.\n6. Design a test or observation plan when practical.\n\n## Output contract\n\n- Behavior diagnosis\n- Principle -> mechanism -> intervention table\n- Ethical risk check\n- Measurement or experiment suggestion\n\n## Quality gate\n\n- The principle explains a real mechanism\n- The intervention is concrete\n- No unsupported certainty\n- No deceptive persuasion pattern\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"
}