Update to PrePilot Lite

{
  "description": "Use when the user needs a reusable marketing context for a brand, product, client, campaign, or offer. Captures audience, pains, alternatives, differentiation, proof, objections, voice, goals, and constraints.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 248
    }
  ],
  "name": "brand-context",
  "skill_md_contents": "---\nname: brand-context\ndescription: Use when the user needs a reusable marketing context for a brand, product, client, campaign, or offer. Captures audience, pains, alternatives, differentiation, proof, objections, voice, goals, and constraints.\n---\n\n# Brand Context Builder\n\n## Use it for\n\n- New client or brand onboarding\n- Product marketing context\n- Refreshing a stale brief\n- Making later marketing outputs more consistent\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- Capture only evidence the user supplied or that can be verified.\n- Use customer language where available instead of corporate phrasing.\n- Distinguish brand-level facts from campaign-specific choices.\n- Do not force B2B persona fields onto consumer products or vice versa.\n\n## Workflow\n\n1. Summarize the product, business model, market, and current objective.\n2. Define priority audience and buying context, including trigger, job, desired outcome, obstacle, and risk.\n3. List real alternatives, including doing nothing, manual work, incumbent tools, and competitors.\n4. Define differentiated value and the proof that supports each important claim.\n5. Capture objections, anti-audiences, switching friction, voice rules, prohibited claims, and operational constraints.\n6. Record the KPIs and decisions this context should support.\n\n## Output contract\n\n- A compact Brand Context document\n- An evidence table for claims and proof\n- A short list of missing inputs ranked by decision impact\n\n## Quality gate\n\n- Every major claim has a proof status\n- Audience description includes behavior or job context, not demographics alone\n- Voice guidance contains concrete do/don't examples\n- The context is reusable across later skills\n\n## Voice calibration from real samples\n\nWhen the user supplies previous writing, treat it as stronger evidence than a generic style checklist. Infer recurring vocabulary, sentence rhythm, paragraph shape, opening and closing habits, level of directness, humor, uncertainty, punctuation, and patterns that are consistently absent. Preserve contradictions instead of smoothing them into a synthetic \"perfect\" voice. A voice rule should be traceable to the user's samples or an explicit preference.\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"
}