simmer-tradejournal

What This Skill Does

The simmer-tradejournal skill acts as an intelligent repository for your trading history, connecting directly to the Simmer markets API to pull, store, and analyze your activities. It transforms raw trade data into actionable intelligence by tracking outcomes, calculating win rates, and determining net profit and loss. Beyond simple tracking, it allows you to annotate trades with qualitative data such as your trading thesis and confidence levels, providing a foundation for meaningful performance reviews through its built-in report generation features.

Installation

To integrate this tool into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/adlai88/simmer-tradejournal

Once installed, ensure your authentication is configured by setting the required environment variable: export SIMMER_API_KEY=your_actual_api_key_here

Use Cases

This skill is designed for traders who rely on data-driven decision-making. Key use cases include:

• Post-Market Analysis: Use daily or weekly reports to identify which market sectors or strategies yield the best returns.
• Performance Calibration: Compare your historical confidence levels against actual outcomes to identify cognitive biases or over-trading habits.
• Portfolio Cleanup: Quickly export your trading history to CSV for deep-dive analysis in external spreadsheets or accounting software.
• Contextual Learning: By using the Python log_trade function, you can enrich every executed order with a specific "thesis," making it easier to review why you made a specific bet months later.

Example Prompts

1. "OpenClaw, pull my latest trade data from Simmer and tell me my win rate for this week."
2. "Generate a monthly performance report and export it to a file named 'january_trades.csv'."
3. "Show me the last 5 trades I made and include the thesis notes for each one so I can review my rationale."

Tips & Limitations

• Sync Regularly: The system requires active polling. Make it a habit to run --sync and --sync-outcomes before checking your reports to ensure the data is current.
• Annotation: The true power of this tool lies in the log_trade function. Don't just track the outcome; use the confidence parameter to build a feedback loop that highlights when you are "right for the wrong reasons."
• Storage: Data is stored locally in data/trades.json. Ensure this file is backed up periodically if you move to a new machine.