prediction-trade-journal

What This Skill Does

The prediction-trade-journal skill provides a robust framework for tracking, analyzing, and improving your performance in prediction markets. By integrating directly with the Simmer Markets API, this agent automates the tedious process of manual trade logging. It captures trade details including market questions, sides taken, share counts, and cost basis. Beyond simple logging, the tool tracks outcomes automatically, allowing you to generate comprehensive reports on your win rate, cumulative P&L, and strategy effectiveness. By enriching your trade history with subjective metadata like your original thesis and confidence levels, the skill helps you perform deep calibration analysis, turning raw trade data into actionable insights to refine your predictive edge over time.

Installation

To integrate this skill into your environment, use the OpenClaw command-line interface. Run the following command in your terminal:

clawhub install openclaw/skills/skills/adlai88/prediction-trade-journal

After installation, ensure your environment is configured correctly by setting your API credentials:

export SIMMER_API_KEY=your_actual_api_key_here

Verify your setup by running the help command or checking the configuration with python tradejournal.py --config.

Use Cases

This skill is perfect for:

• Professional Traders: Maintaining a disciplined ledger for risk management and historical performance reviews.
• Analytical Researchers: Testing whether high-confidence predictions actually outperform random guesses.
• Copy Traders: Evaluating the success rate of mirroring specific whale wallets or strategies by tracking the downstream outcomes of copied trades.
• Portfolio Managers: Reviewing weekly or monthly P&L summaries to allocate resources toward the most profitable market sectors.

Example Prompts

1. "OpenClaw, pull my latest trade history and give me a summary of my performance over the last 30 days."
2. "Can you generate a weekly report for me? I want to see how my high-confidence trades compared to my overall win rate."
3. "Export my entire trade history into a CSV file named monthly_analysis.csv so I can review it in Excel."

Tips & Limitations

To maximize the utility of this skill, utilize the log_trade Python function to inject context into your records. A trade without a 'thesis' is just data; a trade with a thesis allows you to see if you were 'right for the wrong reasons' or if your strategy is actually flawed. Be aware that this skill performs local file writes to data/trades.json, so ensure your storage directory has appropriate write permissions. If trades aren't showing up as resolved, remember to trigger the --sync-outcomes command frequently, as market resolution latency varies across different prediction platforms.