strategy-generate

Automate creation, backtesting, and evaluation of quantitative trading strategies.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/day18708433173-crypto/TradingAgents-Pro --skill strategy-generate-day18708433173-crypto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: strategy-generate
Source: https://github.com/day18708433173-crypto/TradingAgents-Pro/tree/main/agent/src/skills/strategy-generate
Command: npx skills add https://github.com/day18708433173-crypto/TradingAgents-Pro --skill strategy-generate-day18708433173-crypto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy.

What problem does it solve?

This skill automates the end-to-end quantitative trading workflow, removing the manual burden of coding signal logic, managing data sources, and performing rigorous backtesting.

Core Features & Use Cases

  • Automated Strategy Design: Parses user intent to generate signal logic for A-shares, US stocks, Hong Kong stocks, and cryptocurrencies.
  • Integrated Backtesting: Executes backtests using a built-in engine with support for custom indicators, position management, and statistical validation.
  • Iterative Optimization: Provides a structured review process to identify bugs, refine parameters, and improve strategy performance based on empirical metrics.

Quick Start

Use the strategy-generate skill to build a dual moving average crossover strategy for 000001.SZ using 5-day and 20-day windows for the year 2024.

Frequently Asked Questions about strategy-generate

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

FAQPage Schema
How do I backtest a quantitative trading strategy without coding signal logic manually?

Backtesting a quantitative trading strategy is automated by parsing your natural language requirements into configuration files, executing signal engine code, and validating performance through statistical tests.

Can I use pandas and numpy to calculate custom indicators for A-shares and cryptocurrency backtesting?

Pandas and numpy are required dependencies for calculating custom indicators and executing signal logic across A-shares, US stocks, Hong Kong stocks, and cryptocurrencies.

What is the process for optimizing trading strategy parameters based on empirical metrics?

Optimizing trading strategy parameters involves an iterative review process that identifies bugs, refines configurations, and improves empirical performance metrics through structured validation.

Does this quantitative workflow support integrating with external market data providers for historical analysis?

Historical analysis is supported by integrating with various market data providers to fetch asset data, enabling comprehensive backtesting and signal validation across multiple asset classes.

How do I generate a dual moving average crossover strategy for a specific stock window?

Generating a dual moving average crossover strategy requires providing the asset ticker, moving average windows, and target year, which the engine parses into executable signal logic.

What are the limitations of automated strategy generation for quantitative trading?

Automated strategy generation requires pandas and numpy environments and depends on external market data providers, meaning data availability and quality directly constrain backtesting accuracy.