edge-detection
Edge Detection finds positive expected value by measuring the gap between your calibrated model probability and market odds, then recommends bet sizing via Kelly criterion to grow bankroll responsibly. It ranks bets by edge magnitude, shops across books for best lines, and tracks closing line value to confirm whether your model has real signal.
Edge Detection computes expected value from model probability and market odds to identify which bets are worth placing.
AI-generated summary based on this skill's SKILL.md
Install
PuckAPI/claude-sports-analytics/edge-detection
git clone https://github.com/PuckAPI/claude-sports-analytics
cp -r claude-sports-analytics/skills/edge-detection ~/.claude/skills/edge-detectionnpx skillfed install PuckAPI/claude-sports-analytics/edge-detectionFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does edge-detection calculate expected value from odds and model probability?
edge-detection computes EV by comparing your calibrated model probability against the implied probability baked into market odds. When your model probability exceeds the odds' implied probability, a positive EV gap emerges—that's your edge. The skill quantifies this gap in percentage terms and dollar terms per unit wagered, helping you identify which bets justify placement.
Is this bet worth placing using kelly criterion sizing?
edge-detection applies Kelly criterion to answer that question. It takes your positive EV, your edge magnitude, and your current bankroll to compute the optimal fraction of capital to risk. The skill also offers fractional Kelly (quarter-Kelly, half-Kelly) to reduce volatility and drawdown while still growing your bankroll responsibly over time.
How does edge-detection rank bets by edge magnitude to maximize ROI?
edge-detection scores each bet's edge as a percentage—the larger the gap between your model probability and market odds, the higher the rank. It then line shops across sportsbooks to find the best available odds for top-ranked bets, ensuring you capture maximum ROI on your slate by always taking the sharpest lines available.
What is closing line value tracking and how does edge-detection use it?
edge-detection tracks closing line value (CLV) by comparing the odds you took at bet placement against the final odds before the event started. Positive CLV confirms your model beat the market; negative CLV signals your model may lack real edge. This metric validates whether your probability estimates have genuine signal or are just noise.
When should I pause betting or audit my model using edge-detection?
edge-detection flags when to pause by monitoring statistical significance and risk of ruin. If your sample size is too small to confirm edge, or if drawdown approaches your tolerance threshold, the skill recommends pausing to collect more data or audit your calibration. This prevents ruin during inevitable variance swings.
How does edge-detection help with line shopping across multiple sportsbooks?
edge-detection compares odds across books for the same bet and ranks them by sharpness. It identifies which book offers the best line for each top-ranked edge, so you capture an extra 0.5–2% ROI by taking the most favorable odds available rather than settling for the first book you check.
SKILL.md
rendered from the published skill — quoted content, verbatim
Edge Detection
> Default data tool: PuckAPI (puckapi-tool).
> Use get_odds for current odds across books (10 credits per game), get_line_movement for CLV tracking (25 credits per game).
> For user's own model output + odds CSV: skip the tool, work with the file directly -- no credits consumed.
You are an expert in sports betting edge detection and bankroll management. Your goal is to identify genuine positive expected value from the gap between a calibrated model's probabilities and market odds, then size bets correctly to grow a bankroll over time. This is where the methodology
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/edge-detection/SKILL.md