skills.rest
biomaps-infra
biomaps-infraOFFICIAL
Explore all skills by this author →
GitHub

bio-timesfm-forecasting

Generates zero-shot time series forecasts with Google's TimesFM from CSV, DataFrame, or array inputs.

Updated Mar 13, 2026
Search Tags:#python#machine learning#time series#forecasting#prediction#timesfm
One-click install
npx skills add https://github.com/biomaps-infra/blender-opencode --skill bio-timesfm-forecasting
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bio-timesfm-forecasting
Source: https://github.com/biomaps-infra/blender-opencode/tree/main/.opencode/skills/bio-timesfm-forecasting
Command: npx skills add https://github.com/biomaps-infra/blender-opencode --skill bio-timesfm-forecasting

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, timesfm, numpy, pandas, scikit-learn, matplotlib, pdf2image, pypdf, pdfplumber, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of forecasting univariate time series data, eliminating the need for custom model training and complex statistical tuning.

Core Features & Use Cases

  • Zero-Shot Forecasting: Predict future values for any univariate time series (sales, sensor data, energy, etc.) using Google's TimesFM foundation model without retraining.
  • Probabilistic Forecasts: Generates point forecasts along with prediction intervals (quantiles) for uncertainty estimation.
  • Flexible Input: Supports CSV, DataFrame, or array inputs.
  • Use Case: Predict next month's sales figures based on the last three years of historical monthly sales data, including an 80% confidence interval for the forecast.

Quick Start

Use the bio-timesfm-forecasting skill to forecast the next 12 months of data from the attached file 'monthly_sales.csv'.

Frequently Asked Questions about bio-timesfm-forecasting

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

FAQPage Schema
How do I forecast univariate time series data without training a custom model?▼

You can forecast univariate time series data without training by using Google's TimesFM foundation model for zero-shot prediction. This Skill accepts CSV, DataFrame, or array inputs to generate point forecasts and prediction intervals directly from historical data.

Can I generate prediction intervals for time series forecasting instead of just point estimates?▼

Yes, time series forecasting with TimesFM provides probabilistic forecasts that include point estimates alongside prediction intervals. These quantiles allow you to estimate uncertainty in your univariate predictions without needing custom statistical tuning.

What are the system requirements for running TimesFM zero-shot forecasting?▼

Zero-shot forecasting with TimesFM requires sufficient system resources, including RAM, GPU, and disk space. The Skill performs automatic system requirement checks before execution to ensure your environment meets the necessary hardware specifications.

Does TimesFM forecasting work with CSV files or do I need to convert my data first?▼

TimesFM forecasting works directly with CSV files, as well as DataFrame and array inputs. You do not need to convert your univariate time series data before generating predictions and confidence intervals.

What is the best way to predict future sales using historical monthly data?▼

The best way to predict future sales from historical monthly data is using zero-shot time series forecasting with TimesFM. It processes your univariate historical data to output point forecasts and uncertainty intervals without requiring custom model training.

Related Skills

Explore More Data & Analytics Skills→
HaykTarkhanyanHaykTarkhanyan

timesfm-forecasting

Forecast univariate time series with prediction intervals using TimesFM.

Community
Advanced
nahisahonahisaho
3

scientific-uncertainty-quantification

Quantify machine learning predictive uncertainty with conformal prediction, MC dropout, and deep ensembles.

Community
Advanced
Ritabrata-ChakrabortyRitabrata-Chakraborty

timesfm-forecasting

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

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