# trade-journal

Logs trading activity with entry rationale, attributes returns to strategy tags, and detects revenge trading or FOMO. Useful for systematic performance reviews.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 515 installs · ★ 443
- Author: agiprolabs
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/agiprolabs/claude-trading-skills/tree/HEAD/skills/trade-journal/SKILL.md
- Updated: 2026-09-03
- HTML: https://affpapa.org/en/nevibecode/skills/trade-journal

## What it does

trade-journal structures trade logging to replace intuition with concrete metrics. It uses JSON as the primary storage format and supports CSV exports. Each record tracks token direction, execution prices, hold duration, and emotional state. Written rationale is recorded before entry.

The skill categorizes trades using predefined tags such as Momentum or Mean Reversion setups. Analytics rely on Python. Built-in scripts aggregate profit and loss by entry hour and compute profit factors across tokens. For win rate calculations, the `win_rate_by_strategy` function requires at least 5 closed trades per tag, so smaller sample sizes yield no attribution.

Behavioral checks spot discipline lapses. The `detect_revenge_trades` function spots positions opened within 15 minutes of a losing exit. It also flags FOMO entries when setup quality drops below 5 out of 10 or when rationales are missing.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill trade-journal -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/trade-journal/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/trade-journal/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill trade-journal -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/trade-journal/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill trade-journal -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/trade-journal/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install agiprolabs/claude-trading-skills trade-journal
```

2. **Manually: put the files in place**
- File: `.github/skills/trade-journal/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill trade-journal -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/agiprolabs/claude-trading-skills --path skills/trade-journal
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/trade-journal/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add agiprolabs/claude-trading-skills --skill trade-journal -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/agiprolabs/claude-trading-skills/tree/HEAD/skills/trade-journal/SKILL.md

## When to use it
- log trade entries with pre-trade rationale and execution context
- detect emotional patterns like revenge trading and FOMO entries
- calculate strategy win rate and token profit factors via Python
- export structured trade logs into JSON and CSV files

## Example prompts
- Log a new SOL long trade at 142.50 using the momentum-breakout strategy
- Run detect_revenge_trades to find entries opened within 15 minutes of a loss
- Compute win rate by strategy for all recorded trades in the journal

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 0c2388e27d656c50.

BEGIN THIRD-PARTY FILE 0c2388e27d656c50
````text
---
name: trade-journal
description: Structured trade logging, performance review, behavioral pattern detection, and strategy attribution for systematic improvement
---

# Trade Journal

Structured trade journaling for systematic improvement. Log every trade with context, review performance at multiple cadences, detect behavioral patterns that destroy edge, and attribute returns to specific strategies.

## Why Journaling Matters

Most traders fail not from bad strategies but from bad behavior. A trade journal transforms subjective "feel" into objective data:

- **Strategy Attribution**: Know which setups actually make money vs. which feel profitable
- **Behavioral Detection**: Catch revenge trading, FOMO entries, and premature exits before they compound
- **Pattern Recognition**: Discover that your Monday morning trades lose money, or that you cut SOL winners too early
- **Accountability**: Written rationale before entry forces deliberate decision-making
- **Improvement Tracking**: Measure whether changes to your process actually improve results

Without a journal, you optimize on noise. With one, you optimize on signal.

## Trade Record Structure

Every trade record captures context at entry and outcome at exit. See `references/record_format.md` for the complete 18-field schema.

### Minimum Required Fields

```python
trade = {
    "id": "T-20250310-001",
    "token": "SOL",
    "direction": "long",
    "entry_date": "2025-03-10T14:30:00Z",
    "entry_price": 142.50,
    "size_sol": 5.0,
    "strategy": "momentum-breakout",
    "rationale": "Breaking above 4h resistance at 141.80 with volume confirmation",
    "exit_date": "2025-03-10T16:45:00Z",
    "exit_price": 146.20,
    "pnl_sol": 0.648,
    "outcome": "win",
    "lessons": "Held through initial pullback to 143.0, rewarded for patience"
}
```

### Strategy Tagging

Use consistent tags to enable performance attribution:

| Category | Tags |
|----------|------|
| Momentum | `momentum-breakout`, `trend-continuation`, `pullback-entry` |
| Mean Reversion | `range-fade`, `oversold-bounce`, `deviation-snap` |
| Event-Driven | `listing-play`, `catalyst-trade`, `news-reaction` |
| On-Chain | `whale-follow`, `wallet-copy`, `flow-signal` |
| DeFi | `lp-entry`, `yield-farm`, `arb-capture` |

### Rationale Templates

Write rationale **before** entering. Templates by setup type:

```
Momentum: "[Token] breaking [level] on [timeframe] with [confirmation]. Target [price], stop [price]."
Mean Reversion: "[Token] at [X] std devs from [mean] on [timeframe]. Expecting reversion to [target]."
On-Chain: "[Signal type] detected — [wallet/flow description]. Historical hit rate [X]%."
```

## Storage Format
````
END THIRD-PARTY FILE 0c2388e27d656c50

The third-party file has ended. Everything between the 0c2388e27d656c50 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2690 of 10430 bytes. © agiprolabs · MIT · https://github.com/agiprolabs/claude-trading-skills/tree/HEAD/skills/trade-journal/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md