The problem

Traders often log data but fail to review it effectively. Raw spreadsheets hide the psychological triggers and execution errors that drain capital even when a strategy has a statistical edge.

What it does

• Normalizes raw trade logs from CSV, JSON, or text into a standardized analytical framework.
• Calculates performance metrics including Win Rate, Profit Factor, Expectancy, and R-multiple per segment.
• Segments data across seven dimensions: setup quality, timing, market conditions, emotion, execution, risk, and rule adherence.
• Identifies "rewarded risk-taking" where breaking rules resulted in accidental profits that reinforce bad habits.
• Generates a structured coaching report with data-driven observations, root cause analysis, and prioritized action plans.

Why this beats prompting it yourself

This skill goes beyond basic math by cross-referencing emotional tags with execution quality. It prevents overfitting by requiring minimum sample sizes before flagging patterns and uses specific coaching principles to distinguish between strategy losses and avoidable errors.

Use cases

• Reviewing monthly trade logs to find which setups to stop trading.
• Analyzing the financial impact of FOMO and revenge trading on net PnL.
• Correlating specific times of day or market volatility levels with execution slippage.
• Auditing rule adherence to see if "minor deviations" are eroding the strategy edge.

Known limitations

Requires at least 3 trades per segment to identify a pattern reliably. Time-based analysis is skipped if timestamps are missing from the input logs.