Update to MUSITU Axiom

{
  "description": "Perform time-series diagnostics, structural-break analysis, forecasting, regime analysis, and forecast validation using MUSITU Axiom.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 271
    },
    {
      "relative_path": "references/COMMERCIAL.md",
      "size_in_bytes": 751
    },
    {
      "relative_path": "references/PROOF.md",
      "size_in_bytes": 537
    },
    {
      "relative_path": "references/QUALITY.md",
      "size_in_bytes": 2262
    },
    {
      "relative_path": "references/ROUTING.md",
      "size_in_bytes": 504
    },
    {
      "relative_path": "scripts/proof_envelope.py",
      "size_in_bytes": 1023
    },
    {
      "relative_path": "scripts/scenario_grid.py",
      "size_in_bytes": 691
    }
  ],
  "name": "musitu-time-series-forecasting",
  "skill_md_contents": "---\nname: musitu-time-series-forecasting\ndescription: \"Perform time-series diagnostics, structural-break analysis, forecasting, regime analysis, and forecast validation using MUSITU Axiom.\"\n---\n# MUSITU Time-Series & Forecasting\nRead `references/QUALITY.md`.\n\n## Workflow\n1. Validate chronology, frequency, missingness and duplicates.\n2. Diagnose trend, seasonality, breaks and regimes.\n3. Select an appropriate exposed MUSITU operation.\n4. Use holdout or rolling validation when feasible.\n5. Compare plausible specifications.\n6. Produce uncertainty-aware forecasts or scenarios.\n7. Stress extrapolation and structural-break assumptions.\n8. Return horizon-specific reliability and invalidation conditions.\n"
}