Update to PrePilot Lite

{
  "description": "Use when the user wants growth ideas, acquisition or retention experiments, growth loops, referral mechanics, activation ideas, experiment prioritization, or a disciplined way to test growth hypotheses.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 238
    }
  ],
  "name": "growth-experiments",
  "skill_md_contents": "---\nname: growth-experiments\ndescription: Use when the user wants growth ideas, acquisition or retention experiments, growth loops, referral mechanics, activation ideas, experiment prioritization, or a disciplined way to test growth hypotheses.\n---\n\n# Growth Experiments\n\n## Use it for\n\n- Growth backlog\n- Acquisition or activation experiments\n- Retention or referral loops\n- Prioritizing uncertain growth bets\n- Reviewing experiment results\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- Growth ideas must connect to a bottleneck or opportunity in the customer behavior model.\n- Prefer experiments that create learning, not activity.\n- Do not label routine execution as an experiment unless a hypothesis and decision rule exist.\n- Promotion from test to standard practice requires readback evidence.\n\n## Workflow\n\n1. Define the growth equation or funnel stage and current constraint.\n2. Generate hypotheses tied to acquisition, activation, retention, revenue, referral, or a compounding loop.\n3. Specify mechanism, target segment, expected behavior change, and risk.\n4. Prioritize by impact, confidence, effort, speed of learning, and reversibility.\n5. Design the smallest valid test and measurement plan.\n6. After results, decide stop, iterate, expand, or operationalize.\n\n## Output contract\n\n- Growth diagnosis\n- Prioritized experiment backlog\n- Experiment cards with hypothesis, change, metric, duration/evidence threshold, and decision rule\n- Readback template\n\n## Quality gate\n\n- Each experiment answers a decision\n- Metrics include guardrails\n- No false precision on expected lift\n- Successful tests still require operational feasibility\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"
}