multi-attempt-comparison

Compare and rank strategy attempts by Sharpe ratio, total return, and drawdown.

33|2|Updated May 13, 2026
One-click install
npx skills add https://github.com/adennng/stock_strategy_lab --skill multi-attempt-comparison
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-attempt-comparison
Source: https://github.com/adennng/stock_strategy_lab/tree/main/src/strategy_lab/skills/critic_agent/multi-attempt-comparison
Command: npx skills add https://github.com/adennng/stock_strategy_lab --skill multi-attempt-comparison

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps identify the best strategy attempts among multiple versions by comparing their performance and providing recommendations for further optimization or rollback.

Core Features & Use Cases

  • Multi-Attempt Comparison: Evaluate and rank multiple strategy attempts based on performance metrics.
  • Recommendation Generation: Provide suggestions for which attempts to continue optimizing, rollback, or discard.
  • Use Case: When comparing different versions of a trading strategy, use this Skill to determine which attempt has the best overall performance and should be used for further optimization.

Quick Start

Compare and evaluate the attempts 'attempt_001', 'attempt_002', and 'attempt_003' from the 'run_state_path'.

Frequently Asked Questions about multi-attempt-comparison

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

FAQPage Schema
How do I compare multiple trading strategy backtest results to find the best one?

To compare multiple trading strategy backtest results, evaluate key performance metrics like Sharpe ratio, total return, and drawdown across all attempts. This ranks each version to identify the optimal strategy for further optimization or rollback.

What metrics are used for quantitative trading strategy comparison?

Quantitative trading strategy comparison uses metrics including the Sharpe ratio, total return, and drawdown. These indicators evaluate risk-adjusted performance to determine which strategy attempt yields the best overall results.

Can I evaluate multiple optimization artifacts from a single run state path?

Yes, you can evaluate multiple optimization artifacts from a single run state path. By analyzing attempts like attempt_001, attempt_002, and attempt_003, the evaluation generates recommendations on which versions to continue optimizing, rollback, or discard.

How do I generate recommendations for trading strategy rollback or further optimization?

To generate recommendations for trading strategy rollback or further optimization, compare the performance metrics of multiple strategy attempts. The evaluation provides specific suggestions on which attempts to discard, rollback, or continue optimizing based on their results.

What is the best way to rank strategy attempts in a quantitative trading workflow?

The best way to rank strategy attempts in a quantitative trading workflow is by comparing their backtest results across various performance metrics. This identifies the attempt with the best overall performance for continued use.