weekly-performance-digest

---
name: weekly-performance-digest
description: Use when the user wants a weekly performance summary from closed trades — win rate, expectancy, profit factor, R-multiple, MAE/MFE, and win/loss pattern breakdowns.
category: Performance
version: 1.0.0
tools: []
---

# Weekly Performance Digest

Aggregate the trades closed during a week into a single performance report — pure calculation, descriptive only, no trade recommendations.

## When to Use

Use at the end of a trading week to review aggregate realized performance; to measure win rate and expectancy across all closed positions; to see which source skills, exit reasons, sectors, or mechanisms drove wins vs. losses; to feed a month-end review (combine four weekly digests) or a postmortem; or for a quick "what worked / what didn't" snapshot grounded in real closed trades.

Do not use this for a single-trade deep review (use `trade-performance-coach`), for signal-level true/false-positive classification (use `signal-postmortem`), or for buy/sell recommendations or position sizing — this skill is descriptive only.

## Inputs

Read CLOSED theses tracked by `trader-memory-core` for the requested date range (default: trailing 7 days). A trade counts in a week if its actual exit date falls in that range and its status is CLOSED.

## How It Works

**Win/loss.** A trade with positive realized P&L is a winner, negative is a loser, zero is breakeven; win rate = winners / total trades.

**R-multiple.** P&L divided by (entry price − stop-loss price) × shares, using the plan's recorded stop-loss.

**Double-counting safeguard.** A CLOSED thesis's cumulative realized P&L already includes all trims plus the final leg — headline metrics use that cumulative value over CLOSED theses only. Partial trims from theses that are still open (PARTIALLY_CLOSED) are reported separately as informational and are never added into the headline totals or win rate. A position trimmed in week 1 and closed in week 2 therefore shows as a partial trim in week 1 and inside week 2's CLOSED headline — that is intended, not a duplicate.

## Workflow

Compute headline metrics: win rate, expectancy, profit factor, average R-multiple, and MAE/MFE. Break results down across multiple pattern dimensions: source skill, exit reason, thesis type, sector, mechanism tag, and screening grade. Surface the week's biggest winners, losers, and process-improvement lessons.

## Output

Return, in chat, a report with:

- **Summary** — total trades, winners, losers, breakeven, win rate, expectancy, profit factor, total realized P&L (dollar and percent).
- **Metrics** — average/largest winner and loser, average holding days for winners vs. losers, R-multiple average and standard deviation, average MAE% and MFE%.
- **Pattern analysis** — win/loss breakdown by source skill, exit reason, thesis type, sector, mechanism tag, and screening grade.
- **Partial trims** — count and total realized P&L from trims on still-open positions, kept separate from headline totals.
- **Lessons** — top wins, top losses, and process improvements.

An empty week still produces a valid report with zeroed metrics rather than an error.

## Key Principles

1. **Closed trades only for headline numbers** — cumulative outcome figures, keyed on exit date.
2. **No double-counting** — partial trims are informational and excluded from totals.
3. **Pattern attribution** — every win/loss is attributed across multiple dimensions.
4. **Descriptive, not prescriptive** — the digest reports; the user decides.