strategy-generate

strategy-generate lets you design trading strategies by defining entry/exit logic, then automatically backtests them across stocks, crypto, and other instruments. Write your signal engine in Python, configure your parameters, and the skill handles data loading and performance analysis—no boilerplate required.

strategy-generate creates and backtests quantitative trading strategies by writing signal logic and evaluating performance metrics.

AI-generated summary based on this skill's SKILL.md

★ 28,096 ⁮ 4,557 MIT updated 2026-07-27 by HKUDS

Install

HKUDS/Vibe-Trading/strategy-generate · repository language: Python

Manual (git clone) CLI (skillfed)

git clone https://github.com/HKUDS/Vibe-Trading
cp -r Vibe-Trading/agent/src/skills/strategy-generate ~/.claude/skills/strategy-generate

npx skillfed install HKUDS/Vibe-Trading/strategy-generate

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I create a quantitative trading strategy with strategy-generate?

strategy-generate lets you design trading strategies by defining entry/exit logic in Python, then automatically backtests them across stocks, crypto, and other instruments. Write your signal engine with custom conditions, configure your parameters, and the skill handles data loading and performance analysis—no boilerplate required.

Can strategy-generate backtest a trading idea on historical data?

Yes. strategy-generate backtests your strategy across historical price data, evaluating how your entry/exit conditions would have performed. The skill generates performance metrics and trading signals automatically, letting you validate your idea before deploying it live.

What does strategy-generate use to generate trading signals?

strategy-generate generates trading signals based on the custom signal logic you define in Python. You specify your indicators, thresholds, and conditions; the skill applies them to historical and real-time data to produce entry and exit signals for your strategy.

How does strategy-generate optimize position sizing and risk management?

strategy-generate lets you design position sizing and risk management rules within your strategy definition. Configure your position sizing logic, stop-loss levels, and portfolio constraints; the skill applies them during backtesting and evaluation to show how your risk parameters affect overall performance.

Can I optimize trading strategy parameters with strategy-generate?

Yes. strategy-generate supports parameter optimization and validation across multiple markets and instruments. Test different configurations of your entry/exit logic, position sizing, and risk rules to find the settings that maximize your strategy's performance metrics.

What markets and assets does strategy-generate support?

strategy-generate works with stocks, cryptocurrencies, and other instruments. Build and backtest algorithmic trading strategies across any market where you have historical price data, then validate performance before deploying your strategy live.

SKILL.md

rendered from the published skill — quoted content, verbatim

Workflow

Requirements parsing: parse user intent, extract instrument codes, time range, and strategy logic, then write config.json
Strategy design: think through the 5 questions of data / signal / position sizing / backtest / validation
Strategy coding: write code/signal_engine.py (following the SignalEngine contract)
Syntax check: bash("python -c \"import ast; ast.parse(open('code/signal_engine.py').read()); print('OK')\"")
Run backtest: call the backtest tool (built into the engine; no need to write run_backtest.py)
Evaluate results: read artifacts/metrics.csv and judge by the review criteria
Iterative fixing: if results are poor, modify with edit_file → run backtest → re-evaluate

You only need to write signal_engine.py and config.json. The backtest tool automatically handles data loading and backtest execution.

Requirements Parsing

Extract the following from the user's description: - Instrument codes: process them according to the

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 2 files

agent/src/skills/strategy-generate/SKILL.md
agent/src/skills/strategy-generate/examples.md

All skills by HKUDS →