backtest-diagnose

Diagnose failed Python backtests by inspecting artifacts, code, and configuration.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/Liangwei-zhang/six-stock --skill backtest-diagnose-liangwei-zhang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: backtest-diagnose
Source: https://github.com/Liangwei-zhang/six-stock/tree/main/Vibe-Trading/agent/src/skills/backtest-diagnose
Command: npx skills add https://github.com/Liangwei-zhang/six-stock --skill backtest-diagnose-liangwei-zhang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps diagnose failed or underperforming backtests, identify root causes, and guide fixes to restore or improve performance.

Core Features & Use Cases

  • Read existing artifacts to inspect metrics, equity, and trades
  • Inspect code and configuration to classify issues and propose fixes
  • Re-run validation after applying fixes to verify improvement

Quick Start

Run the failing backtest, then use this skill to read artifacts, diagnose the root cause, apply a fix, and re-validate results.

Frequently Asked Questions about backtest-diagnose

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

FAQPage Schema
How do I diagnose a failed Python backtest using metrics and trade artifacts?

To diagnose a failed Python backtest, inspect existing artifacts like metrics, equity, and trades to identify root causes. This process classifies runtime errors, logic bugs, and data issues, guiding specific fixes to restore performance.

Why does my backtest underperform and how do I find the root cause?

An underperforming backtest often stems from logic bugs or data issues. Reviewing artifacts and configuration helps classify issues per an error taxonomy, pinpointing the root cause and proposing fixes to improve results.

Can I re-validate backtest results after applying code and configuration fixes?

Yes, you can re-validate backtest results after applying fixes. Re-running the validation process verifies whether the applied changes successfully resolved the runtime errors or improved the underperforming metrics.

What is the best way to classify backtest issues when debugging Python trading logic?

The best way to classify backtest issues is by applying an error taxonomy after inspecting code, configuration, and artifacts. This categorizes problems into runtime errors, logic bugs, or data issues to guide targeted fixes.

Does backtest diagnosis work with Python-based trading scripts that output equity curves?

Yes, backtest diagnosis works with Python-based scripts that output equity curves and trade artifacts. It reads these metrics to inspect performance, identify root causes, and guide fixes for trading logic and data issues.