Update to Creator Workspace

{
  "description": "Analyze a LinkedIn analytics export and, when a coding workspace is available, build an interactive local dashboard plus data-backed recommendations. Use when the user supplies LinkedIn analytics CSV/XLSX data or asks for a performance dashboard.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 298
    }
  ],
  "name": "analytics-dashboard",
  "skill_md_contents": "---\nname: analytics-dashboard\ndescription: Analyze a LinkedIn analytics export and, when a coding workspace is available, build an interactive local dashboard plus data-backed recommendations. Use when the user supplies LinkedIn analytics CSV/XLSX data or asks for a performance dashboard.\n---\n\n# LinkedIn Analytics Dashboard\n\n## Inputs\n\nAccept LinkedIn exports in CSV or spreadsheet form. Use only fields actually present.\n\n## Analysis\n\nWhen Python or another deterministic data tool is available:\n\n1. inspect schema and date range\n2. clean missing values and obvious type issues\n3. calculate post-level and period-level metrics\n4. separate totals from rates\n5. identify outliers\n6. compare formats, topics, posting times, and structural features only where data supports the comparison\n\n## Dashboard path\n\nIf the current host provides a coding workspace and the user wants a dashboard, create a simple local React or static HTML dashboard with:\n\n- summary KPIs\n- trend view\n- top and bottom posts\n- filterable post table\n- format/topic breakdown when fields support it\n- recommendation panel\n\nIf no coding workspace exists, return the analysis as tables and narrative instead.\n\n## Recommendations\n\nGive 5 recommendations. Every recommendation must cite a specific pattern from the uploaded data and include the relevant metric or comparison.\n\nDo not present correlation as proof of causation.\n\n## Visual handoff\n\nIf a local dashboard, comparison board, or report is created, use `show-me` principles for the final artifact and verify the generated file when the host supports preview.\n\n## Creator Workspace handoff\n\nUse `sandbox-python-executor` for calculations. Hand the verified findings to `show-me` when the user wants a dashboard or visual comparison.\n"
}