Update to Creator Workspace

{
  "description": "Create a post, newsletter, script, carousel, infographic outline, or other content grounded in the user's second-brain context. Use when the user says create from my brain, use my notes, use my research, or wants content that draws on stored knowledge.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 285
    }
  ],
  "name": "create-from-brain",
  "skill_md_contents": "---\nname: create-from-brain\ndescription: Create a post, newsletter, script, carousel, infographic outline, or other content grounded in the user's second-brain context. Use when the user says create from my brain, use my notes, use my research, or wants content that draws on stored knowledge.\n---\n\n# Create From Brain\n\n## 1. Retrieve narrowly\n\nFind the smallest set of relevant wiki pages, source notes, project state, and voice files. Do not dump the entire brain into context.\n\n## 2. Separate evidence from interpretation\n\nList the claims that are directly supported and the claims that are the user's interpretation. Preserve uncertainty.\n\n## 3. Choose the authorship path\n\n- If the user supplied spoken material and wants the piece to remain literally theirs, use `voiceprint`.\n- If they want normal drafting in a learned style, use `voice-builder` profile plus the relevant writing skill.\n- If no voice profile exists, use current instructions and examples only.\n\n## 4. Choose the format\n\nRoute to the specific social or writing skill, not a generic catch-all.\n\n## 5. Visual handoff\n\nIf the output includes a comparison, plan, design directions, or dashboard, use `show-me` after the content is correct.\n\n## 6. Provenance\n\nDo not invent facts to fill gaps. When a source claim matters, keep enough provenance that the user can trace it back.\n\n## 7. End state\n\nDeliver the requested content. Do not automatically save new memory unless the user invokes `save-progress`.\n\n## Creator Workspace handoff\n\nUse `workspace-recall` first when the relevant workspace context has not already been retrieved. Then route to the narrowest production skill and apply voice rules when available.\n"
}