Can I aggregate results at a portfolio level?

Yes, by using the --aggregate flag, the skill will generate a combined forecast representing the sum or average of all processed time series.

What is the main benefit of the Nixtla Batch Forecaster?

It allows you to forecast dozens or hundreds of time series in parallel, significantly reducing the total processing time compared to sequential API calls.

What data format is required for batch forecasting?

Your input CSV must follow the Nixtla schema, containing 'unique_id' (series identifier), 'ds' (timestamp), and 'y' (the numeric value to forecast).

How does the skill handle API rate limits?

The skill includes a configurable delay parameter and batch-size controls to ensure your requests stay within your TimeGPT tier limits while maintaining maximum throughput.

Do I need a Nixtla API key to use this skill?

Yes, you must set the NIXTLA_TIMEGPT_API_KEY environment variable to authenticate with the TimeGPT service and run the forecasting engine.

Nixtla Batch Forecaster

Name: Nixtla Batch Forecaster
Author: intent-solutions-io

byintent-solutions-io

Data Science & ML

Forecasts multiple time series in parallel using TimeGPT to optimize throughput and portfolio analysis.

About

The Nixtla Batch Forecaster skill enables Claude to manage large-scale time series prediction tasks by leveraging the TimeGPT API. It streamlines the process of forecasting 10 to 100+ individual contracts or data streams concurrently, handling complexities like rate limiting, data validation, and automated fallback. This skill is particularly useful for financial analysts, supply chain managers, and developers building prediction markets who need efficient, aggregated insights across diverse data portfolios with production-grade reliability.

Key Features

Built-in data validation for Nixtla-compatible schemas
Portfolio-level data aggregation and summary reporting
Parallel batch processing for high-throughput time series forecasting
Automated rate limiting and error-aware retry logic
0 GitHub stars
Flexible configuration for forecast horizons and frequencies

Use Cases

Generating daily demand forecasts for large-scale retail inventory management
Predicting market prices across a portfolio of 100+ prediction market contracts
Analyzing hourly energy consumption patterns for distributed utility grids

About

Key Features

Built-in data validation for Nixtla-compatible schemas
Portfolio-level data aggregation and summary reporting
Parallel batch processing for high-throughput time series forecasting
Automated rate limiting and error-aware retry logic
0 GitHub stars
Flexible configuration for forecast horizons and frequencies

Use Cases

Generating daily demand forecasts for large-scale retail inventory management
Predicting market prices across a portfolio of 100+ prediction market contracts
Analyzing hourly energy consumption patterns for distributed utility grids