pair-trading

Calculate Z-scores of price ratios to generate long-short mean-reversion signals.

Updated Jul 8, 2026
One-click install
npx skills add https://github.com/hxhyyy/Vibe-Trading --skill pair-trading-hxhyyy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pair-trading
Source: https://github.com/hxhyyy/Vibe-Trading/tree/main/agent/src/skills/pair-trading
Command: npx skills add https://github.com/hxhyyy/Vibe-Trading --skill pair-trading-hxhyyy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy.

What problem does it solve?

This Skill addresses the challenge of identifying and executing mean-reversion trades between two correlated financial instruments, removing the need for manual spread monitoring and calculation.

Core Features & Use Cases

  • Z-Score Analysis: Automatically calculates the rolling mean and standard deviation of the price ratio between two assets to identify statistical anomalies.
  • Automated Signal Generation: Triggers long/short signals based on configurable Z-score thresholds to capture expected price convergence.
  • Use Case: A trader can use this to monitor a pair like BTC/ETH or two stocks in the same sector, automatically entering a long-short hedge when the spread deviates significantly from the historical mean.

Quick Start

Use the pair-trading skill to generate signals for the BTC-USDT and ETH-USDT pair using a 60-day lookback window.

Frequently Asked Questions about pair-trading

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

FAQPage Schema
How do I calculate the Z-score for a mean-reversion trading strategy?▼

This skill calculates the Z-score for mean-reversion trading by computing the rolling mean and standard deviation of the price ratio between two correlated financial instruments, generating long-short signals based on statistical deviation thresholds.

How do I automate long-short signal generation for correlated crypto assets?▼

You can automate long-short signal generation for correlated crypto assets by configuring Z-score thresholds, which triggers entry signals capturing expected price convergence when the spread deviates significantly from the historical mean.

Do I need pandas and numpy to run quantitative trading calculations?▼

Yes, you need pandas and numpy to run these quantitative trading calculations, as the skill requires them for executing rolling window calculations and vectorizing the long-short trading signals.

Can I use a 60-day lookback window to monitor a BTC and ETH trading pair?▼

Yes, you can use a 60-day lookback window to monitor a BTC and ETH trading pair, generating automated long-short hedge signals when the price ratio spread deviates from the historical mean.

What is the best way to identify statistical anomalies in asset price ratios?▼

The best way to identify statistical anomalies in asset price ratios is calculating the Z-score of the spread, which highlights when current prices deviate significantly from historical rolling averages to signal mean-reversion.

When should I not use a mean-reversion approach for quantitative trading?▼

You should not use a mean-reversion approach when the statistical correlation between the two financial instruments breaks down, as the Z-score signals become invalid if the assets stop exhibiting historically correlated price ratios.