Diagnose failed backtests by classifying errors and editing signal_engine.py.
npx skills add https://github.com/loanntc/Paave --skill backtest-debugger
Please help me install this Agent Skill. Skill: backtest-debugger Source: https://github.com/loanntc/Paave/tree/main/skills/backtest-diagnose Command: npx skills add https://github.com/loanntc/Paave --skill backtest-debugger
Backtests that fail or produce poor performance are hard to debug without systematically inspecting both the outputs and the underlying signal logic; this Skill identifies the root cause and guides targeted repairs.
artifacts/metrics.csv, artifacts/equity.csv, and artifacts/trades.csv to classify failures such as runtime errors, abnormal results, and suspicious trading behavior.code/signal_engine.py and config.json to pinpoint issues like data mapping mismatches, sizing logic bugs, missing exit handling, or dependency-related runtime errors.edit_file, reruns the backtest, and validates outcomes by re-checking updated metrics.csv (including hard-gate checks like non-empty artifacts, NaN-free equity, and exit_code == 0).Use the backtest-debugger skill to diagnose why your backtest failed or underperformed by inspecting the generated artifacts and updating the signal engine code until the rerun passes validation.
High-intent search queries and answers about installing and using this skill.
Debug failed backtests by inspecting artifacts like `metrics.csv`, `equity.csv`, and `trades.csv` to classify failures, then reviewing `signal_engine.py` to pinpoint data mapping mismatches or sizing logic bugs causing zero trades or abnormal equity curves.
Backtesting strategies leave positions open or generate late trades due to missing exit handling or logic bugs in the signal engine code, requiring targeted edits in `signal_engine.py` and validation through rerunning metrics checks.
Diagnose NaN values or empty data conditions in backtest artifacts by mapping symptoms to an error taxonomy across `metrics.csv` and `equity.csv`, making precise edits in the signal engine, and validating with hard-gate checks for NaN-free equity.
Fix Python backtesting runtime errors by reviewing `signal_engine.py` and `config.json` to identify dependency-related issues or data mapping mismatches, applying edits, and rerunning the backtest until `exit_code == 0`.
Validate backtest fixes automatically by rerunning the strategy and applying hard-gate checks to updated `metrics.csv`, confirming non-empty artifacts, NaN-free equity curves, and `exit_code == 0` to ensure repaired backtests pass validation.
HKUDSDiagnose failed trading backtests by inspecting artifacts and signal_engine code.
0xZKnwAutomate design, coding, and backtesting of quantitative trading strategies.
darkounus90Generate a one-page market posture summary from breadth, regime, and flow signals.
NigarumOvumParse trade journal files and generate trading behavior diagnostics and profile metrics.