Update to PrePilot Lite

{
  "description": "Use when the user needs paid-media strategy, account review, budget allocation, campaign structure, audience strategy, bidding logic, Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, creative planning, pacing, or spend diagnosis.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 227
    }
  ],
  "name": "paid-media",
  "skill_md_contents": "---\nname: paid-media\ndescription: Use when the user needs paid-media strategy, account review, budget allocation, campaign structure, audience strategy, bidding logic, Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, creative planning, pacing, or spend diagnosis.\n---\n\n# Paid Media\n\n## Use it for\n\n- Paid-media planning\n- Read-only performance review\n- Budget and pacing decisions\n- Campaign structure and targeting\n- Cross-platform test planning\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- Never assume live account access or current platform capabilities.\n- For current policies, inventory, targeting, bidding, attribution, or product changes, verify current primary sources when tools are available.\n- Separate platform-reported results from incrementality and business outcomes.\n- Do not recommend spend changes from weak evidence without stating uncertainty and safeguards.\n\n## Workflow\n\n1. Define business goal, conversion event, economics, audience, market, budget, existing data, and tracking confidence.\n2. Diagnose measurement quality before interpreting platform performance.\n3. Assign platform and campaign roles based on demand state and available creative.\n4. Design campaign structure, audience approach, bidding hypothesis, budget/pacing, and exclusions.\n5. Define creative hypotheses and landing-page message match.\n6. Set review cadence, thresholds, and readback fields before spending or changing spend.\n\n## Output contract\n\n- Paid-media plan or audit\n- Budget/pacing logic\n- Campaign and audience structure\n- Creative and landing hypotheses\n- Measurement and decision rules\n- Risks and verification needs\n\n## Quality gate\n\n- No fake benchmarks\n- Economics and tracking confidence are visible\n- Recommendations have a reason and a decision rule\n- No hidden assumption that platform attribution equals true incrementality\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"
}