trading-algorithm

Guide quantitative trading algorithm development with walk-forward validation and Kelly criterion.

1|Updated Dec 4, 2025
One-click install
npx skills add https://github.com/Espenator/elite-trading-system --skill trading-algorithm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trading-algorithm
Source: https://github.com/Espenator/elite-trading-system/tree/main/docs/updated-skills/trading-algorithm
Command: npx skills add https://github.com/Espenator/elite-trading-system --skill trading-algorithm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides expert guidance on designing, implementing, and validating sophisticated trading algorithms, ensuring robust risk management and maximizing profitable edges.

Core Features & Use Cases

  • Strategy Design: Develops and refines trading strategies based on market regimes, signal generation, and risk-adjusted returns.
  • Risk Management: Enforces strict rules for position sizing, portfolio heat, and drawdown limits.
  • Validation: Implements rigorous backtesting methodologies like walk-forward validation to prevent overfitting and ensure out-of-sample performance.
  • Use Case: When considering a new momentum swing trading strategy, this Skill will guide the process from defining entry/exit rules and position sizing using half-Kelly, to setting up walk-forward validation and ensuring it meets target Sharpe ratios and drawdown limits.

Quick Start

Use the trading-algorithm skill to analyze the provided backtest results for potential overfitting and suggest improvements to the walk-forward validation process.

Frequently Asked Questions about trading-algorithm

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

FAQPage Schema
How do I prevent overfitting when backtesting a quantitative trading algorithm?

Prevent overfitting in a trading algorithm by using walk-forward validation and analyzing out-of-sample performance metrics. This ensures your strategy's edge is statistically valid rather than a product of historical curve fitting.

What is the best way to calculate position sizing for a trading strategy?

Calculate position sizing using the Kelly criterion to optimize risk-adjusted returns. Applying half-Kelly balances maximizing profitable edges with strict risk management and portfolio heat constraints to control drawdowns.

How does market regime detection work in algorithmic trading?

Market regime detection identifies varying market conditions to refine trading strategies and signal generation. Adapting to these regimes allows algorithms to adjust risk controls and optimize entries based on distinct market environments.

Can I use machine learning for signal generation in a trading algorithm?

Yes, machine learning can drive signal generation within a trading algorithm. The strategy design must enforce strict risk management rules and validate signals using walk-forward testing to maintain statistical reliability.

Why does my trading strategy fail out-of-sample despite a high backtest Sharpe ratio?

A trading strategy failing out-of-sample despite a high backtest Sharpe ratio indicates overfitting. Implementing walk-forward validation and strict drawdown limits ensures out-of-sample performance metrics remain statistically valid.