strategy-generate

Generate configuration and signal logic for quantitative trading backtests.

Updated Apr 19, 2026

Search Tags:#python #strategy #trading #backtest #quantitative #config-json #signal-engine

Ready to run

npx skills add https://github.com/ajithkumar31082004-bit/Vibe-Trading --skill strategy-generate-ajithkumar31082004-bit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: strategy-generate
Source: https://github.com/ajithkumar31082004-bit/Vibe-Trading/tree/main/Vibe-Trading-main/agent/src/skills/strategy-generate
Command: npx skills add https://github.com/ajithkumar31082004-bit/Vibe-Trading --skill strategy-generate-ajithkumar31082004-bit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the end-to-end process of designing, implementing, and evaluating quantitative trading strategies, reducing manual handoffs and speeding up backtests.

Core Features & Use Cases

End-to-end workflow: from parsing user intent to generating a Python signal engine and config for backtesting.
Backtest-ready outputs: produces config.json and code/signal_engine.py aligned with the engine's contract, ready for the backtest tool.
Iterative optimization: supports multiple iterations by adjusting signals and re-running backtests to improve metrics.

Quick Start

Define a new strategy configuration and a corresponding signal engine, then run the built-in backtester to evaluate performance.

Frequently Asked Questions about strategy-generate

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

FAQPage Schema

How do I generate a backtest-ready config and signal engine for quantitative trading?▼

Generate backtest-ready quantitative trading outputs by creating a config.json and signal_engine.py that align instrument codes, time ranges, and performance criteria into a deterministic backtest workflow.

What is the best way to automate end-to-end strategy design and backtesting in Python?▼

Automate end-to-end strategy design by parsing trading intent to generate Python signal logic and configuration files, reducing manual handoffs and speeding up backtest iterations.

How does index alignment work between trading signals and backtest inputs?▼

Index alignment between trading signals and backtest inputs is enforced by the signal_engine.py contract, ensuring deterministic mapping of generated signals to specified instrument codes and time ranges.

Can I iteratively optimize quantitative trading strategies by adjusting signals?▼

Iteratively optimize quantitative trading strategies by adjusting signal logic and re-running backtests to improve performance metrics across multiple evaluation cycles.

Does the backtest workflow support hard-coded dates and instrument codes?▼

The backtest workflow explicitly excludes hard-coded dates and instrument codes, requiring all time ranges and instrument parameters to be captured dynamically within the config.json structure.

What prerequisites do I need to run a quantitative backtest workflow?▼

Running a quantitative backtest workflow requires specifying instrument codes, time ranges, and performance criteria, which are wired into deterministic inputs without external dependencies.