Generate quantitative trading strategies with config.json and signal_engine.py backtests.
npx skills add https://github.com/loanntc/Paave --skill strategy-builder-loanntc
Please help me install this Agent Skill. Skill: strategy-builder Source: https://github.com/loanntc/Paave/tree/main/skills/strategy-generate Command: npx skills add https://github.com/loanntc/Paave --skill strategy-builder-loanntc
This Skill turns vague trading ideas into a runnable quantitative strategy by generating the required configuration and signal engine code, then validating the results through a backtest workflow.
config.json.code/signal_engine.py that follows the required SignalEngine contract and outputs signals in the range [-1.0, 1.0].artifacts/metrics.csv and other outputs, and iteratively refine until criteria are met.Ask the system to create a strategy for AAPL.US using a clear entry/exit rule, then run the backtest for 2024 and return the metrics.
High-intent search queries and answers about installing and using this skill.
To build and backtest a quantitative trading strategy, you translate your trading intent into a valid config.json and a SignalEngine implementation, then run a backtest to evaluate metrics and iteratively refine the strategy logic.
Yes, the signal engine supports backtesting crypto, China A-shares, US stocks, and Hong Kong stocks by applying market data normalization rules to format instrument codes for daily long, short, or portfolio strategies.
Signal outputs must be constrained to the range [-1.0, 1.0], signal indices must align to input data, and the signal_engine.py code must avoid unsafe execution blocks to pass risk validation.
You evaluate backtest results by running the built-in backtest tool and inspecting the generated artifacts, specifically the metrics.csv file, to review performance and iteratively refine your strategy until criteria are met.
The default time range for a backtest is 10 years back when omitted, allowing the requirements parsing step to extract a broad historical window for evaluating long-term equity or crypto strategy performance.
Yes, you can generate a portfolio weighting strategy by defining your intent during requirements parsing, which produces a config.json and signal engine implementation designed to handle portfolio-style allocations across supported markets.
heximaoFetch real-time market data and generate stock analysis reports.
GGwujunDiagnose failed backtests by analyzing artifacts, code, and configurations.
DaddyElonMusk69Generate config.json and signal_engine.py for backtesting quantitative trading strategies.
ebrahim-saniGenerate and test quantitative trading strategies into a backtest-ready signal engine.