skills.rest
recallnet
recallnetOFFICIAL
Explore all skills by this author →
Website𝕏@recallnetGitHub

timesfm-forecasting

Forecast univariate time series with TimesFM zero-shot forecasting.

1|Updated Apr 28, 2026
Search Tags:#forecasting#time-series#preflight#zero-shot#timesfm#covariates
One-click install
npx skills add https://github.com/recallnet/polymarket-cross-sectional-momentum --skill timesfm-forecasting-recallnet
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: timesfm-forecasting
Source: https://github.com/recallnet/polymarket-cross-sectional-momentum/tree/main/.agents/skills/timesfm-forecasting
Command: npx skills add https://github.com/recallnet/polymarket-cross-sectional-momentum --skill timesfm-forecasting-recallnet

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, torch, timesfm, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Forecasts univariate time series without training a custom model by leveraging TimesFM's zero-shot forecasting.

Core Features & Use Cases

  • Zero-shot forecasting for sales, sensor readings, energy demand, or other univariate time series.
  • Supports basic forecasting and covariate forecasting (XReg) with dynamic and static exogenous variables.
  • Includes a mandatory preflight memory check that validates RAM/GPU availability and dataset fit before loading the model.

Quick Start

Run the preflight system check first, then load TimesFM and forecast your first univariate series.

Frequently Asked Questions about timesfm-forecasting

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I forecast a univariate time series from a CSV without training a model?▼

You can forecast a univariate time series from a CSV without training a model by using TimesFM zero-shot forecasting. The skill processes CSV, DataFrame, and array inputs directly to generate future predictions.

Can I include exogenous variables for covariate forecasting in TimesFM?▼

Yes, covariate forecasting is supported using XReg. You can include dynamic and static exogenous variables alongside your univariate time series to enhance your zero-shot predictions.

Do I need to check RAM or GPU availability before loading the TimesFM model?▼

Yes, a mandatory preflight memory check validates RAM and GPU availability before loading the TimesFM model. The skill includes a preflight script to ensure your system can handle the dataset fit.

What is zero-shot time-series forecasting and when should I use it?▼

Zero-shot time-series forecasting predicts future values without training a custom model on your specific data. Use it for sales, sensor readings, or energy demand when you lack the data or resources for custom training.

Does TimesFM work with pandas DataFrames and numpy arrays?▼

Yes, TimesFM works with pandas DataFrames and numpy arrays. The skill accepts CSV, DataFrame, and array inputs to forecast your univariate time series data.

Related Skills

Explore More Data & Analytics Skills→
crazymsncrazymsn
22

timesfm-forecasting

Forecast univariate time-series with TimesFM from CSV, DataFrame, or arrays.

Community
Advanced
sagunkayasthasagunkayastha

timesfm-forecasting

Forecast univariate time series with Google's TimesFM foundation model.

Community
Intermediate
dralkhdralkh
74

timesfm-forecasting

Forecast univariate time series with TimesFM and generate prediction intervals.

Community
Advanced
RamanEbrahimiRamanEbrahimi
3

timesfm-forecasting

Generates zero-shot time-series forecasts and prediction intervals from CSV, DataFrame, or array inputs using Google's TimesFM foundation model and torch library.

Community
Advanced