aster-timesfm-pipeline

Name: aster-timesfm-pipeline
Availability: InStock
Author: kmshihab7878

Connect Aster DEX klines to TimesFM for zero-shot crypto price forecasts.

6|1|Updated Apr 7, 2026

Search Tags:#mcp #forecasting #time-series #crypto #aster #timesfm #quantiles

Ready to run

npx skills add https://github.com/kmshihab7878/claude-code-setup --skill aster-timesfm-pipeline

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: aster-timesfm-pipeline
Source: https://github.com/kmshihab7878/claude-code-setup/tree/main/skills/aster-timesfm-pipeline
Command: npx skills add https://github.com/kmshihab7878/claude-code-setup --skill aster-timesfm-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides an end-to-end pipeline that pulls historical klines from the Aster DEX, transforms market data into numeric series, and produces zero-shot point forecasts with quantile prediction intervals via TimesFM to support trading signal generation and risk assessment.

Core Features & Use Cases

Aster MCP ingestion: retrieve historical klines and optional funding rates at multiple intervals for any supported trading pair.
TimesFM forecasting: run TimesFM 2.5 to generate point forecasts and full quantile prediction intervals for uncertainty-aware decisions.
Batch multi-pair processing: forecast many pairs in a single batch for efficient signal generation and portfolio-level risk analysis.
Risk-aware rules: interpret quantile spreads for position sizing, backtest forecast accuracy, and reduce exposure when uncertainty is high.
Use Case: produce 24-hour hourly forecasts for BTCUSDT to inform trade entry/exit decisions and assess downside/upside risk via the 10th–90th percentiles.

Quick Start

Request a 24-hour hourly forecast for BTCUSDT with quantile intervals and return the point forecast plus the 10th and 90th percentile bounds.

Frequently Asked Questions about aster-timesfm-pipeline

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

FAQPage Schema

What is zero-shot crypto forecasting with quantiles?▼

Zero-shot crypto forecasting with quantiles uses pre-trained models like TimesFM to predict future prices without task-specific training, returning point forecasts alongside percentile intervals for uncertainty-aware trading decisions.

How do I get hourly crypto price forecasts with prediction intervals?▼

To get hourly crypto price forecasts with prediction intervals, you pull historical klines from Aster DEX, format the time series into numpy arrays, and run TimesFM to generate 24-hour point forecasts with 10th–90th percentile bounds.

Can I run multi-pair crypto forecasting in a single batch?▼

Yes, you can run multi-pair crypto forecasting in a single batch to efficiently generate trading signals for multiple pairs like BTCUSDT, ETHUSDT, and SOLUSDT simultaneously for portfolio-level risk analysis.

Do I need Aster MCP klines access for TimesFM forecasting?▼

Yes, you need Aster MCP klines access to retrieve historical market data, along with numpy-formatted time series, TimesFM 2.5 model availability, sufficient compute, and network access to download the model.

How are quantile spreads used for position sizing in crypto?▼

Quantile spreads from TimesFM forecasts are used for position sizing by adjusting exposure based on uncertainty; wider spreads signal higher risk, allowing you to reduce position size and backtest forecast accuracy for risk-aware decisions.