Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Trading Journal Performance Auditor

    1

    Audit trading journals and strategy logs using deterministic statistics to find behavioral leaks and verify edge.

    $20

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Trading Journal Performance Auditor

    Trading Journal Performance Auditor

    Example session with this skill installed

    Audit my recent 45 trades from this CSV. My starting equity was $10,000 and I trade the 5-minute NQ opening range. Can you tell me if I have a real edge or if I'm just lucky?

    • Read your context and instructions
    • Compiled the trading journal performance

    I have processed 45 trades from your provided log. The audit used a starting equity of $10,000 USD.

    DISCLAIMER: This report is for educational purposes only and does not constitute investment advice. Trading involves significant risk of loss.

    Performance Audit Report: 2023-10-27

    Executive Summary
    The strategy shows a positive expectancy but high profit concentration. 42% of total gains came from 2 trades, suggesting the edge is sensitive to outliers. Behavioral flags indicate increased risk-taking immediately following losing streaks.

    Core Metrics

    MetricValueInterpretation
    Sample Size45Low confidence (Needs >100 for significance)
    Win Rate48.8%Moderate
    Profit Factor1.62Healthy (>1.40)
    Expectancy (R)0.28RPositive
    Max Drawdown8.4%Within typical parameters
    Bootstrap 95% CI[-0.05, 0.61]Spans zero; edge not yet proven

    Scorecard

    • Edge evidence: 2/5 (Sample size is small; CI spans zero).
    • Risk control: 4/5 (Consistent R-multiple usage noted).
    • Cost efficiency: 3/5 (Slippage on NQ fills is eating 12% of gross profit).
    • Consistency: 2/5 (Monthly returns vary significantly).
    • Process discipline: 3/5 (Detected 4 instances of "revenge" sizing).
    • Record quality: 5/5 (All timestamps and fee columns provided).

    Behavioral Patterns

    Evidence shows a "recency bias" where position sizes increase by 20% after two consecutive losses. This has contributed to 35% of your total drawdown.

    Live Benchmark (As of 2023-10-27)

    Your return of +7.2% outperformed the Nasdaq-100 (QQQ) benchmark of +2.1% over the same period. However, your realized volatility was 3x higher than the index.

    Next steps

    1. Implement a "cool-down" rule: no trading for 2 hours after two consecutive stops to mitigate size-drift.
    2. Collect 55 more trades to reach the 100-trade significance threshold.
    3. Review the 2 largest winners to see if they were "plan-compliant" or accidental windfalls.

    DISCLAIMER: This report is for educational purposes only and does not constitute investment advice.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Most traders rely on "vibes" and gut feelings to judge their performance, leading to blown accounts and unaddressed behavioral leaks. This skill replaces subjective analysis with a deterministic audit of your actual trade history to identify whether your results stem from a statistical edge or simple luck.

    What it does

    • Statistical auditing calculates win rate, expectancy, profit factor, and SQN using a deterministic Python script.
    • Robustness testing performs bootstrap confidence interval analysis and Monte Carlo simulations to model ruin risk.
    • Behavioral detection flags patterns like revenge trading, overtrading, and inconsistent position sizing after losses.
    • Market benchmarking fetches live market data to compare your equity curve against relevant indices and volatility regimes.
    • Segmentation analysis breaks down performance by symbol, setup, weekday, and entry hour to find hidden alpha.

    How it works

    1. Intake provides a CSV/XLSX file of closed trades or uses the included journal template to format your data.
    2. Analysis runs the core audit script to generate a JSON metrics object and a raw markdown report.
    3. Benchmarking retrieves live data to adjust for market context and fee drag.
    4. Reporting delivers a structured performance scorecard with process-based experiments for the next 30 days.

    Frameworks & tools

    The skill utilizes Python 3.8+ with Pandas/OpenPyxl for data processing. It requires web search capabilities for live market benchmarking and uses standard statistical methods like bootstrapping for significance testing.

    Why this beats prompting it yourself

    Generic prompts often hallucinate math or fail to account for survivorship bias and sample size significance. This skill uses a hardened Python script for calculations, ensuring your drawdown and expectancy figures are mathematically accurate rather than estimated.

    Use cases

    • Strategy validation to determine if a backtest or small live sample has a statistically significant edge.
    • Psychological auditing to pinpoint exactly when and how emotions lead to deviation from your plan.
    • Broker export analysis to clean and audit messy trade logs from MetaTrader, NinjaTrader, or Interactive Brokers.
    • Journaling setup to implement a professional-grade record-keeping system with pre-trade checklists.

    Known limitations

    Analysis of samples under 30 trades is limited to hypothesis generation. It cannot analyze open positions or provide real-time trade signals. Live benchmarking requires an active web search tool.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.

    Samples under 30 trades are treated as anecdotal. Requires CSV/XLSX input. No real-time signals or investment advice. Live benchmarking depends on tool availability.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 11 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed11 days ago

    What's inside

    Frequently Asked Questions

    The skill supports standard CSV and XLSX exports from major platforms like MetaTrader, NinjaTrader, and Interactive Brokers. It also includes a specialized journal template to help you format manual entries for the most accurate analysis.

    Unlike generic AI prompts that may hallucinate math, this skill uses a deterministic Python script for all calculations. This ensures that critical metrics like Profit Factor, SQN, and Drawdown are mathematically precise rather than just estimated.

    You receive the core Python-based auditing engine, a structured journal template for data logging, and the capability to generate detailed PDF/Markdown performance scorecards. It also includes the Monte Carlo simulation tool for ruin risk modeling.

    For statistically significant results, a sample of at least 30 closed trades is recommended. While the skill can analyze smaller datasets, the resulting confidence intervals and robustness tests require a larger sample size to distinguish between an actual edge and simple luck.

    Yes, the skill is designed to run on any AI agent platform with Python execution environments and web search capabilities. It uses standard libraries like Pandas and OpenPyxl, ensuring broad compatibility across most modern agent frameworks.

    New in Trading & Investing