Strategy Backtesting Engine for Openclaw

Requirements

• Python 3.7+
• Core dependencies: pandas, numpy, matplotlib
• Install the skill package and dependencies:

pip install backtest-free pandas numpy matplotlib

Basic usage

python -c "import backtest_free; print('backtest_free loaded')"

Example workflow

python - <<'PY'
import backtest_free

strategy = backtest_free.create_strategy()
strategy.set_parameters(stock_code='AAPL', period='1m', risk_threshold=0.05)
results = strategy.run_backtest()
print(results.analyze())
print(results.get_summary())
PY

Configuration notes

• Use environment variables for API credentials instead of hardcoding secrets.
• Ensure source data is reliable and correctly typed before execution.
• Prefer DataFrame-based inputs for larger datasets to improve memory efficiency.
• Verify that file paths, dependencies, and command permissions are valid before running automation.

Input schema

Output schema

{
  "success": true,
  "data": {
    "result": "Strategy backtesting engine processing result",
    "metadata": {
      "skill": "backtest",
      "version": "1.0.0",
      "direction": "financial analysis"
    }
  },
  "error": null
}

Metadata taxonomy

Common result artifacts

• Win rate
• Return rate
• Maximum drawdown
• Visual charts and reports
• Trade signals and risk-control recommendations

Operational notes

• The skill is optimized for structured, repeatable financial analysis workflows.
• It supports batch-style processing and export-friendly outputs.
• It is designed to improve traceability through consistent metadata and validation.