PO

    parameter overfit guard

    1

    Detects settings that only work in narrow historical pockets and builds stability tests around parameter neighborhoods.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more
    PO

    parameter overfit guard

    Example session with this skill installed

    Check my trading strategy parameters (MA: 20, RSI: 70) for overfitting on last year's S&P 500 data. Run a neighborhood test and check for regime sensitivity.

    • Read your context and instructions
    • Compiled the parameter overfit guard

    Stability Report

    • Status: Suspicious (Overfit detected)
    • Neighborhood Test: 5% drop in MA (19) leads to 40% drawdown.
    • Regime Sensitivity: Strategy fails in high-volatility windows.
    • Recommendation: Use MA 22; it shows 12% lower returns but 80% higher neighborhood stability.

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

    About this skill

    Detects settings that only work in narrow historical pockets and builds stability tests around parameter neighborhoods.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    • Requires sufficient historical data for meaningful splits.
    • Cannot predict black swan events outside of simulated regime shifts.
    • Accuracy depends on the quality of provided input data.

    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 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    It uses neighborhood sensitivity testing, perturbing parameters by 1-10% to see if performance collapses, indicating a non-robust spike.

    Yes, it performs walk-forward validation and regime-shift simulations to see how settings hold up against unseen volatility or trends.

    It provides a stability report including a safe parameter range, degradation ratios, and a sensitivity table for neighboring values.