strategy-generate

Name: strategy-generate
Availability: InStock
Author: hxhyyy

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

Updated Jul 8, 2026

Search Tags:#automation #strategy #finance #backtesting #trading #quantitative

Ready to run

npx skills add https://github.com/hxhyyy/Vibe-Trading --skill strategy-generate-hxhyyy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: strategy-generate
Source: https://github.com/hxhyyy/Vibe-Trading/tree/main/agent/src/skills/strategy-generate
Command: npx skills add https://github.com/hxhyyy/Vibe-Trading --skill strategy-generate-hxhyyy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy.

What problem does it solve?

This skill removes the technical friction from quantitative trading by automating the design, coding, and backtesting process for financial strategies across multiple asset classes.

Core Features & Use Cases

Automated Strategy Lifecycle: Handles everything from parsing user intent and generating Python signal logic to executing backtests and evaluating performance metrics.
Multi-Market Support: Seamlessly integrates data from Tushare (A-shares), YFinance (US/HK stocks), and OKX (Crypto) using a unified interface.
Use Case: A user can request a dual moving average crossover strategy for a specific stock, and the agent will automatically generate the signal engine, run the backtest, and provide a performance report with actionable improvement items.

Quick Start

Use the strategy-generate skill to create and backtest a dual moving average crossover strategy for 000001.SZ using 5 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 automate backtesting a quantitative trading strategy across different markets?▼

You can automate backtesting a quantitative trading strategy by generating Python signal logic and executing historical data evaluations across A-shares, US/HK stocks, and Crypto using a unified data interface.

Can I backtest a moving average crossover strategy for a specific stock using historical market data?▼

Yes, you can backtest a moving average crossover strategy for a specific stock by parsing your intent, generating the signal engine, and running automated performance evaluations on historical market data.

Does the strategy generation process require pandas and numpy for quantitative finance analysis?▼

Yes, the strategy generation process requires pandas and numpy to implement the signal engine contract and execute quantitative finance backtesting computations on historical data.

What is the best way to design and evaluate a quantitative trading strategy without manual coding?▼

The best way to design and evaluate a quantitative trading strategy without manual coding is using an automated lifecycle tool that parses intent, generates signal logic, and outputs performance reports with actionable improvement items.

What limitations exist when using YFinance, Tushare, and OKX data for automated strategy backtesting?▼

The primary limitation is that automated strategy backtesting using YFinance, Tushare, and OKX data requires strict adherence to the SignalEngine contract and automated validation of backtest artifacts for accurate results.

Why does my quantitative trading backtest fail during signal engine implementation?▼

Your quantitative trading backtest may fail during signal engine implementation if the generated Python signal logic does not strictly adhere to the required SignalEngine contract for automated validation.