einstein-research-backtest-engine

id	einstein-research-backtest-engine
name	Einstein Research — Backtest Engine
description	Programmatic backtesting framework for trading strategies. Runs backtests with historical price data (yfinance or CSV), supports momentum/mean-reversion/factor/signal-based strategies, walk-forward optimization, out-of-sample testing, transaction cost modeling, regime-aware splits, and full performance metrics (Sharpe, Sortino, Calmar, max drawdown, CAGR, win rate, profit factor). Distinct from einstein-research-backtest (which provides methodology guidance). Use when a user wants to actually run a backtest, test a specific strategy on historical data, or generate performance metrics.
version	1.0.0
author	DaVinci
last_amended_at	null
trigger_patterns	[]
pre_conditions	{"git_repo_required":false,"tools_available":[]}
expected_output_format	natural_language

Backtest Engine

This skill is the programmatic engine for running quantitative trading strategy backtests. It takes a machine-readable strategy definition (e.g., from the einstein-research-edge skill) and executes it against historical data, producing detailed performance metrics.

When to Use This Skill

• User wants to run a backtest on a specific strategy.
• User has a strategy.yaml file from the edge-generator skill.
• User wants to generate performance metrics for a trading idea.
• Triggers: "run a backtest," "test this strategy," "generate performance metrics."

This skill is for execution. For guidance on how to design a robust backtest, see the einstein-research-backtest methodology skill.

Workflow

Step 1: Provide Strategy Definition

The backtest engine requires a strategy.yaml file that defines the rules of the strategy.

strategy.yaml Format:

version: backtest-engine/v1
name: 52-Week High Momentum
universe: "sp500"
data:
  source: yfinance
  start_date: "2018-01-01"
  end_date: "2023-12-31"
entry_signal:
  - "price > high_52w"
  - "volume > 2 * avg_volume_50d"
exit_signal:
  - "hold_days == 5"
  - "pct_change >= 0.10"
  - "pct_change <= -0.05"
parameters:
  hold_days: 5