backtest-diagnose

Diagnose and repair failed algorithmic trading backtests by analyzing execution artifacts and signal engine code.

Updated Jul 8, 2026
One-click install
npx skills add https://github.com/hxhyyy/Vibe-Trading --skill backtest-diagnose-hxhyyy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: backtest-diagnose
Source: https://github.com/hxhyyy/Vibe-Trading/tree/main/agent/src/skills/backtest-diagnose
Command: npx skills add https://github.com/hxhyyy/Vibe-Trading --skill backtest-diagnose-hxhyyy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill resolves failures and performance anomalies in trading backtests by systematically diagnosing runtime errors, logic bugs, and data issues.

Core Features & Use Cases

  • Automated Error Classification: Automatically categorizes issues into runtime errors, logic bugs, or data-source problems based on a predefined taxonomy.
  • Iterative Repair: Provides a structured workflow to inspect artifacts, modify signal engine code, and verify fixes through re-execution.
  • Use Case: If a backtest returns zero trades or unexpected equity results, this skill inspects the signal logic and data configuration to pinpoint and suggest specific code adjustments.

Quick Start

Use the backtest-diagnose skill to analyze the current backtest failure and apply the necessary code fixes to resolve the issue.

Frequently Asked Questions about backtest-diagnose

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

FAQPage Schema
Why does my trading backtest return zero trades or unexpected equity results?

Trading backtests return zero trades or unexpected equity due to runtime errors, logic bugs, or data-filtering issues. Analyzing execution artifacts alongside signal engine source code pinpoints specific code adjustments to resolve these anomalies.

How do I debug an algorithmic trading backtest that is underperforming?

Debug an underperforming algorithmic trading backtest by inspecting metrics, equity, and trade logs. Iterative validation of the signal engine code identifies logic bugs and data-source problems, enabling targeted code modifications for repair.

How do I fix runtime errors in my Python backtesting signal engine?

Fix Python backtesting runtime errors by classifying them against a predefined taxonomy. Inspecting execution artifacts and modifying signal engine code iteratively validates repairs through re-execution to ensure stability.

What data do I need to diagnose a failed algorithmic trading backtest?

Diagnosing a failed algorithmic trading backtest requires access to execution artifacts including metrics, equity, and trade logs. Signal engine source code is also necessary to perform iterative validation and apply code corrections.

Can I use automated error classification to fix backtesting data-filtering issues?

Automated error classification categorizes backtesting data-filtering issues using a predefined taxonomy. This systematic approach distinguishes data-source problems from logic bugs, guiding specific code adjustments within the quantitative environment.

What is the best way to resolve data-source problems affecting trading backtest performance?

Resolving data-source problems affecting trading backtest performance involves analyzing execution artifacts to isolate data-filtering issues. Iterative repair modifies signal engine code and verifies fixes through re-execution to restore expected results.