Update to Creator Workspace

{
  "description": "Import ChatGPT or Claude conversation-export JSON into local markdown files with metadata. Use when the user has exported AI history and wants it organized, searchable, or ready for a second brain.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 286
    }
  ],
  "name": "conversation-importer",
  "skill_md_contents": "---\nname: conversation-importer\ndescription: Import ChatGPT or Claude conversation-export JSON into local markdown files with metadata. Use when the user has exported AI history and wants it organized, searchable, or ready for a second brain.\n---\n\n# Conversation Importer\n\n## Preferred execution\n\nWhen the export is available in the workspace and Python exists, use the bundled script:\n\n```bash\npython3 scripts/conversation_importer.py INPUT OUTPUT_DIR\n```\n\nThe script supports best-effort detection of common ChatGPT and Claude JSON export shapes.\n\n## Safety\n\n- never upload local exports to a third party just to parse them\n- do not expose unrelated conversations in logs\n- preserve the original export files\n- write generated markdown to a separate output directory\n\n## After import\n\n1. inspect several generated files\n2. verify dates and titles look plausible\n3. use `living-wiki` for topic synthesis and linking\n4. do not claim every export format is supported if the parser skipped records\n\n## Fallback\n\nIf Python is unavailable, inspect the export structure with available file tools and convert a small verified batch rather than pretending the whole export was processed.\n\n## Creator Workspace handoff\n\nUse `sandbox-python-executor` for deterministic parsing when available. Hand imported markdown to `living-wiki` when the user wants reusable knowledge, then verify retrieval with `workspace-recall`.\n"
}