skills.rest
Ritabrata-Chakraborty
Ritabrata-ChakrabortyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

timesfm-forecasting

Generate zero-shot probabilistic forecasts for univariate time series with TimesFM.

Updated Jun 6, 2026
Search Tags:#time series forecasting#TimesFM#probabilistic forecasting#univariate time series#zero-shot forecasting
One-click install
npx skills add https://github.com/Ritabrata-Chakraborty/Claude-Setup --skill timesfm-forecasting-ritabrata-chakraborty
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: timesfm-forecasting
Source: https://github.com/Ritabrata-Chakraborty/Claude-Setup/tree/main/skills/timesfm-forecasting
Command: npx skills add https://github.com/Ritabrata-Chakraborty/Claude-Setup --skill timesfm-forecasting-ritabrata-chakraborty

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides zero-shot time series forecasting using Google's TimesFM foundation model, eliminating the need for custom model training and enabling efficient forecasting for univariate time series data.

Core Features & Use Cases

  • Zero-shot Forecasting: Forecast any univariate time series without training a custom model.
  • Probabilistic Forecasts: Generate point forecasts with calibrated quantile prediction intervals.
  • Flexible Input: Supports CSV, DataFrame, and array inputs.
  • Use Case: Use this Skill to forecast sales, energy consumption, or any other univariate time series data without the need for extensive data preprocessing or model training.

Quick Start

Use the timesfm-forecasting skill to forecast the next 24 hours of sales data from the provided CSV file 'sales_data.csv'.

Frequently Asked Questions about timesfm-forecasting

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

FAQPage Schema
What is zero-shot time series forecasting and how does it handle univariate data?▼

Zero-shot time series forecasting predicts future values for univariate data without requiring custom model training. It uses pre-trained foundation models to directly generate forecasts from your historical data inputs.

How do I generate probabilistic forecasts with calibrated prediction intervals?▼

To generate probabilistic forecasts with calibrated prediction intervals, you input your univariate time series data into the forecasting model. The system then outputs point forecasts alongside quantile-based prediction intervals.

Can I use CSV, DataFrame, or array inputs for univariate time series forecasting?▼

Yes, you can process univariate time series forecasting using CSV, DataFrame, or array inputs. The system directly accepts these flexible input formats to analyze historical data and generate future predictions.

Do I need PyTorch or TimesFM installed to perform zero-shot forecasting?▼

Yes, you need both TimesFM and PyTorch installed in your environment. These dependencies are required to process your time series data and execute the foundation model for generating zero-shot forecasts.

What are the limitations of using a foundation model for univariate time series forecasting?▼

This approach is limited to univariate time series forecasting tasks and cannot model multivariate dependencies. It is designed specifically for generating probabilistic forecasts with calibrated prediction intervals for single variables.

What is the best way to forecast sales or energy consumption without training a custom model?▼

The best way to forecast sales or energy consumption without custom training is using zero-shot forecasting. This approach applies pre-trained foundation models directly to your univariate data to generate immediate future predictions.

Related Skills

Explore More Data & Analytics Skills→
recallnetrecallnet
1

timesfm-forecasting

Forecast univariate time series with TimesFM zero-shot forecasting.

Official
Advanced
nferrer-devnferrer-dev

timesfm-forecasting

Performs zero-shot univariate time series forecasting with Google's TimesFM.

Community
Advanced
yf8578yf8578
1

timesfm-forecasting

...

Community
Advanced
Zeyuyang-0420Zeyuyang-0420

timesfm-forecasting

Forecast univariate time series with Google's TimesFM zero-shot model.

Community
Advanced