{
  "description": "Synthetic retail sales data with covariates for TimesFM XReg demo",
  "note_on_real_data": "If using a real dataset (e.g., Kaggle Rossmann Store Sales), download it to a temp directory (tempfile.mkdtemp) and do NOT commit it here. This skills directory only ships tiny reference files.",
  "stores": {
    "store_A": {
      "type": "premium",
      "region": "urban",
      "base_sales": 1000
    },
    "store_B": {
      "type": "standard",
      "region": "suburban",
      "base_sales": 750
    },
    "store_C": {
      "type": "discount",
      "region": "rural",
      "base_sales": 500
    }
  },
  "dimensions": {
    "context_length": 24,
    "horizon_length": 12,
    "total_length": 36,
    "num_stores": 3,
    "csv_rows": 108
  },
  "covariates": {
    "dynamic_numerical": [
      "price",
      "promotion"
    ],
    "dynamic_categorical": [
      "holiday",
      "day_of_week"
    ],
    "static_categorical": [
      "store_type",
      "region"
    ]
  },
  "xreg_modes": {
    "xreg + timesfm": "Fit regression on residuals after TimesFM forecast",
    "timesfm + xreg": "TimesFM forecasts residuals after regression fit"
  },
  "bug_fixes": [
    "v2: Fixed variable-shadowing in generate_sales_data() \u2014 inner dict comprehension `{store_id: ... for store_id in stores}` was overwriting the outer loop variable, causing all stores to get identical covariate arrays. Fixed by using separate per-store dicts during the loop.",
    "v2: Reduced CONTEXT_LEN from 48 \u2192 24 weeks; CSV now 90 rows (was 180)."
  ]
}