agentleFS
SpartanLabsXyzSpartanLabsXyz/simmer-sdk/skills/prediction-trade-journal/SKILL.md

prediction-trade-journal

Skill56 starsChanged 10 days agoMITView on GitHub

Auto-log trades with context, inspect trade history, track win rate and P&L, generate reports, and analyze which strategies work best.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When user asks to install or configure this skill:

    line 16
  2. Very specific:

    Run python tradejournal.py --sync to fetch trades from API

    line 137
  3. Very specific:

    Run python tradejournal.py --sync-outcomes to update resolved markets

    line 140

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Prediction Trade Journal

Track every trade, learn from outcomes, improve your edge.

Setup Flow

When user asks to install or configure this skill:

  1. Install the Simmer SDK
    pip install simmer-sdk
  2. Ask for Simmer API key
    • They can get it from simmer.markets/dashboard → SDK tab
    • Store in environment as SIMMER_API_KEY

Quick Commands

# 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:

  • Base URL: https://api.simmer.markets
  • Auth: Authorization: Bearer $SIMMER_API_KEY
  • Trades: GET /api/sdk/trades

How It Works

  1. Sync - Polls /api/sdk/trades to fetch trade history
  2. Store - Saves trades locally with outcome tracking
  3. Track - Updates outcomes when markets resolve
  4. Report - Generates win rate, P&L, and calibration analysis

CLI Reference

CommandDescription
--syncFetch new trades from API
--history NShow last N trades (default: 10)
--sync-outcomesUpdate resolved markets
--report daily/weekly/monthlyGenerate summary report
--configShow configuration
--export FILE.csvExport to CSV
--dry-runPreview without making changes

Configuration

SettingEnvironment VariableDefault
API KeySIMMER_API_KEY(required)

Storage

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
  }
}

Skill Integration

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.

Example Report

📓 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

Troubleshooting

"SIMMER_API_KEY environment variable not set"

  • Set your API key: export SIMMER_API_KEY=sk_live_...

"No trades recorded yet"

  • Run python tradejournal.py --sync to fetch trades from API

Trades not showing outcomes

  • Run python tradejournal.py --sync-outcomes to update resolved markets

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.