forecasting-reverso
SolidZero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activate when users provide time series data and request forecasts, predictions, or extrapolations. Supports Reverso Small (550K params). Triggers on "forecast", "predict", "time series", "Reverso", or when tabular data with a temporal dimension needs future-value estimation.
Install
Quality Score: 85/100
Skill Content
Details
- Author
- oaustegard
- Repository
- oaustegard/claude-skills
- Created
- 11 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
forecasting-ch15-foundation-models
Use when a pretrained time-series model is being evaluated on a new series under a fixed model revision, or studying forecasting book chapter 15.
timesfm-forecasting
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM/GPU before loading the model, validates dataset fit before processing, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model and handle your specific dataset.
defensible-forecasting
Build defensible time-series forecasts from historical data (sales, GMV, demand, web traffic — any numeric series over time). ALWAYS interview the user first (goal, forecast horizon, output document format, charts yes/no, data structure) before doing anything else. Runs a bundled engine that backtests ~20+ methods across every major forecasting family (rolling-origin CV), selects the best 3 by MAPE with anti-overfitting safeguards (holdout confirmation, parsimony, seasonal data-gating), and outputs a forecast with prediction intervals and a plain-language risk rating. Use whenever the user wants to forecast, predict, or project future numbers from historical data — even when they only say "predict next month's sales", "project demand", "proyeksi penjualan", "peramalan", or "forecast". Trigger for any demand-planning, sales/target-setting, or time-series projection task, even if the word "forecast" is not used.