Auto-log trades with context, track outcomes, generate calibration reports to improve trading.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install prediction-trade-journal或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install prediction-trade-journal⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/prediction-trade-journal/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: prediction-trade-journal displayName: Prediction Trade Journal description: Auto-log trades with context, track outcomes, generate calibration reports to improve trading. metadata: {"clawdbot":{"emoji":"📓","requires":{"env":["SIMMER_API_KEY"]},"cron":null,"autostart":false}} authors: - Simmer (@simmer_markets) version: "1.1.4" published: true ---
Track every trade, learn from outcomes, improve your edge.
Use this skill when the user wants to:
# Sync trades from API
python tradejournal.py --sync
# Show recent trades
python tradejournal.py --history 10
# Generate weekly report
python tradejournal.py --report weekly
# Export to CSV
python tradejournal.py --export trades.csv
API Reference:
https://api.simmer.marketsAuthorization: Bearer $SIMMER_API_KEYGET /api/sdk/trades/api/sdk/trades to fetch trade history| Command | Description | |---------|-------------| | --sync | Fetch new trades from API | | --history N | Show last N trades (default: 10) | | --sync-outcomes | Update resolved markets | | --report daily/weekly/monthly | Generate summary report | | --config | Show configuration | | --export FILE.csv | Export to CSV | | --dry-run | Preview without making changes |
| Setting | Environment Variable | Default | |---------|---------------------|---------| | API Key | SIMMER_API_KEY | (required) |
Trades are stored locally in data/trades.json:
{
"trades": [{
"id": "uuid",
"market_question": "Will X happen?",
"side": "yes",
"shares": 10.5,
"cost": 6.83,
"outcome": {
"resolved": false,
"winning_side": null,
"pnl_usd": null
}
}],
"metadata": {
"last_sync": "2025-01-29T...",
"total_trades": 50
}
}
Other skills can enrich trades with context:
from tradejournal import log_trade
# After executing a trade
log_trade(
trade_id=result['trade_id'],
source="copytrading",
thesis="Mirroring whale 0x123...",
confidence=0.70
)
This adds thesis, confidence, and source to the trade record for better analysis.
📓 Weekly Report
========================================
Period: Last 7 days
Trades: 15
Total cost: $125.50
Resolved: 8 / 15
Win rate: 62.5%
P&L: +$18.30
By side: 10 YES, 5 NO
"SIMMER_API_KEY environment variable not set"
export SIMMER_API_KEY=sk_live_..."No trades recorded yet"
python tradejournal.py --sync to fetch trades from APITrades not showing outcomes
python tradejournal.py --sync-outcomes to update resolved markets安装 Prediction Trade Journal 后,可以对 AI 说这些话来触发它
Help me get started with Prediction Trade Journal
Explains what Prediction Trade Journal does, walks through the setup, and runs a quick demo based on your current project
Use Prediction Trade Journal to auto-log trades with context, track outcomes, generate calibration ...
Invokes Prediction Trade Journal with the right parameters and returns the result directly in the conversation
What can I do with Prediction Trade Journal in my finance & investment workflow?
Lists the top use cases for Prediction Trade Journal, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/prediction-trade-journal/ 目录(个人级,所有项目可用),或 .claude/skills/prediction-trade-journal/(项目级)。重启 AI 客户端后,用 /prediction-trade-journal 主动调用,或让 AI 根据上下文自动发现并使用。
Prediction Trade Journal 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Prediction Trade Journal 可免费安装使用。请查阅仓库了解许可证信息。
Auto-log trades with context, track outcomes, generate calibration reports to improve trading.
Prediction Trade Journal 属于「Finance & Investment」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my finance & investment tasks using Prediction Trade Journal
Identifies repetitive steps in your workflow and sets up Prediction Trade Journal to handle them automatically