Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Prediction Market Edge Analyzer — Find Which Categories Actu

    1

    Turn your Polymarket / Kalshi trade history into a category-by-category edge report: hit rate vs. break-even, expected-value advantage, and a clear verdict on which categories to keep and which to kill.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Prediction Market Edge Analyzer — Find Which Categories Actu

    Example session with this skill installed

    Analyze my Polymarket trades in trades.csv to find which categories have a positive edge and where I am losing the most money.

    • Read your context and instructions
    • Compiled the prediction market edge

    I have analyzed 333 settled trades from your CSV. The data shows a clear divergence between your performance in sports markets versus crypto-related event contracts.

    Prediction Market Performance Audit

    CategoryTradesHit RateAvg EntryBreak-evenEdge (pp)Net PnLResult
    Sports1425.63%0.0323.20%+2.43+$412.50✅ Profitable
    Politics8812.50%0.11511.50%+1.00+$185.00✅ Profitable
    Crypto651.54%0.0282.80%-1.26-$210.00❌ Bleeding
    Social380.00%0.0454.50%-4.50-$150.20❌ Bleeding

    Odds Bracket Breakdown

    BracketTradesWin CountActual Hit RateImplied ProbEdge
    < 2¢4500.00%1.45%-1.45
    2¢ - 5¢19084.21%3.10%+1.11
    5¢ - 10¢6857.35%7.80%-0.45
    > 10¢30413.33%12.10%+1.23

    Summary Findings:
    Your edge is strongest in the

    Sports category within the

    2¢ - 5¢ range. You are significantly overpaying for "moonshot" crypto bets (sub-2¢) where your realized hit rate is zero against an implied cost of 1.45%.

    Next steps

    1. Stop betting on Crypto markets with entry prices below 5¢; these are currently your largest source of drain.
    2. Increase size on Sports markets where entry is between 2¢ and 5¢ to capitalize on your +2.43pp edge.
    3. Export new data after 50 more trades to see if the Social category stabilizes or remains a total loss.

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

    About this skill

    The problem

    Trading low-probability, high-payout markets feels great when you hit one — but you can't actually tell by hand whether you're profitable overall, or which category is quietly bleeding your bankroll.

    The method

    This skill applies one clean principle:

    Break-even hit rate ≈ your entry price. (Buy at 3¢ → you need >3% hit rate to be profitable.) edge = actual hit rate − average entry price

    • edge > 0 → that category has positive expectancy, keep it
    • edge < 0 → structural bleed, cut it

    Output

    A self-contained HTML report plus Markdown summary:

    • KPIs — wins, hit rate, total invested, net P&L, ROI
    • By category — trades, hit rate, break-even rate, edge (pp), average odds, net P&L, verdict
    • By odds band — performance across <2¢ / 2-5¢ / 5-10¢ / 10-20¢ / >20¢ entry ranges
    • Conclusion — automatically lists categories with positive expectancy

    Sample result (333 real trades)

    CategoryTradesHit rateBreak-evenEdgeNet P&LVerdict
    Sports events605.0%3.0%+2.0pp+113✅ Positive
    Crypto1491.3%2.7%−1.4pp−207❌ Negative
    Celebrity/social782.6%3.0%−0.4pp−43❌ Negative

    Insight: inefficiency (and edge) lives in low-liquidity event markets, not in efficiently-priced crypto markets.

    Input

    A generic CSV of your trades — column aliases supported (market/title, entry_price/price, invested/size, realized_profit/pnl, status). Category column optional (auto-inferred from market title).

    Disclaimer

    For research purposes only. Not investment advice.

    Results require at least 50 settled trades for statistical significance. Open positions are automatically excluded from analysis.

    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 any payment.

    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 1 month ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill requires a standard CSV export from Polymarket or Kalshi containing your trade history; if your data is in a different format, a manual ledger following the provided template will also work.

    This skill is designed for use with Python-enabled AI agents and data analysis environments, seamlessly integrating into workflows that support Pandas-based processing.

    You will receive the core logic for the data processing engine, pre-configured analysis parameters for odds brackets, and a template for mapping custom market categories.

    Unlike general PnL trackers, this skill calculates your 'edge' by comparing your actual win rate against the market's implied probability, helping you see if you are truly outperforming the house.

    Because statistical significance requires a baseline of data, we recommend having at least 50 settled trades to ensure the edge calculations and ROI distributions are meaningful.

    The skill is built to handle standard API exports from major markets, and updates are released periodically to accommodate changes in exchange CSV structures or new market categories.

    New in Trading & Investing