Software Development
TimesFM Forecasting
The skill generates zero‑shot time‑series forecasts using Google’s TimesFM, delivering regular‑grid CSVs that include quantile predictions and optional XReg covariates. It evaluates performance on held‑out data and supports both the TimesFM 2.5 checkpoint and the TimesFM 3.0 multivariate API, documenting weight‑license requirements. Data scientists and analysts receive accurate, ready‑to‑deploy forecasts without extensive model tuning.
- Publisher / source
- Scientific Agent Skills
- Upstream record
- K-Dense-AI/scientific-agent-skills
- Version
- Version 7
- Published
- Publication review
- Approved for publication
- Content fingerprint
6f785fe73b133e9af7720fa46cf9013645198950155624889ef611b7b0dc74b8