PuckAPI avatar

PuckAPI

Official

@puckapi · Buffalo, NY

0Followers
|
3Public Repos
|
28Published Skills

The hockey data API. Stats, odds, and everything between.

Skills Distribution
DomainBusiness, Fi...Predictive Modeling (40%)Sports Data Engine.. (30%)Betting Market Ana.. (30%)

Agent Skills by PuckAPI

Showing 28 vetted skills indexed across 1 GitHub repositories.

PuckAPIPuckAPI
2

visualization

Convert sports analytics data into matplotlib and seaborn charts.

Official
Intermediate
PuckAPIPuckAPI
2

prop-modeling

Project NHL player statistics and compare them to sportsbook lines.

Official
Advanced
PuckAPIPuckAPI
2

team-analysis

Analyzes hockey teams' standings, performance metrics, and comparative data.

Official
Intermediate
PuckAPIPuckAPI
2

backtesting

Run walk-forward historical backtests on sports betting models to verify profitability.

Official
Advanced
PuckAPIPuckAPI
2

goalie-analysis

Analyzes NHL goalies' performance, workload, and matchup history using advanced metrics.

Official
Advanced
PuckAPIPuckAPI
2

hockey-analytics

Explain advanced hockey analytics metrics like Corsi, Fenwick, PDO, xG, and RAPM.

Official
Intermediate
PuckAPIPuckAPI
2

puckapi-tool

Retrieve NHL game results, player stats, standings, and betting odds via API.

Official
Basic
PuckAPIPuckAPI
2

dispatch

Routes hockey analytics requests to relevant skills and data sources.

Official
Advanced
PuckAPIPuckAPI
2

feature-engineering

Convert raw hockey data into model-ready features with lagging and rolling windows.

Official
Intermediate
PuckAPIPuckAPI
2

bet-tracker

Log betting entries, resolve outcomes, and analyze profit and loss metrics.

Official
Intermediate
PuckAPIPuckAPI
2

probability-calibration

Calibrate sports prediction model probabilities using logistic or isotonic regression.

Official
Intermediate
PuckAPIPuckAPI
2

elo-engineering

Create multi-variant Elo rating systems for sports teams from historical game data.

Official
Advanced
PuckAPIPuckAPI
2

war-gar-decomposition

Derive WAR and GAR metrics from shift-level RAPM regression models.

Official
Advanced
PuckAPIPuckAPI
2

daily-card

Analyze NHL game odds and calculate betting edges for ranked recommendations.

Official
Intermediate
PuckAPIPuckAPI
2

nl-to-query

Convert natural language hockey questions into structured data queries.

Official
Intermediate
PuckAPIPuckAPI
2

ai-hockey-workflow

Guide hockey analytics workflows with Claude and MCP tools.

Official
Advanced
PuckAPIPuckAPI
2

xg-model-building

Develop shot-level expected goals models from NHL play-by-play data.

Official
Advanced
PuckAPIPuckAPI
2

data-pipeline

Automate sports analytics pipelines for data collection, predictions, and drift detection.

Official
Intermediate
PuckAPIPuckAPI
2

edge-detection

Compare model probabilities against market odds to identify positive expected value bets.

Official
Advanced
PuckAPIPuckAPI
2

odds-explorer

Compare live NHL odds and analyze line movements across sportsbooks.

Official
Intermediate
PuckAPIPuckAPI
2

walk-forward-validation

Perform walk-forward validation for sports prediction models with season-based splitting.

Official
Intermediate
PuckAPIPuckAPI
2

playoff-simulation

Model NHL season outcomes with Monte Carlo simulations to estimate playoff and championship probabilities.

Official
Advanced
PuckAPIPuckAPI
2

totals-modeling

Model NHL game total goals using pace, special teams, goalie matchups, and context.

Official
Advanced
PuckAPIPuckAPI
2

game-preview

Aggregate team, goalie, and betting data into NHL game preview reports.

Official
Advanced

Frequently Asked Questions About PuckAPI

FAQPage Schema
What specific tasks can I perform using PuckAPI?

You can retrieve historical NHL game results, calculate expected goals, perform Monte Carlo playoff simulations, and identify betting edges by comparing model probabilities against live market odds. The platform supports end-to-end sports analytics from raw data ingestion to final profit and loss tracking.

Who is the target persona for these sports analytics capabilities?

PuckAPI is designed for sports data scientists, professional handicappers, and hockey analysts who require granular shift-level data and robust statistical modeling. It serves users building proprietary betting systems or those conducting deep-dive performance research on NHL teams and individual player metrics.

What are the prerequisites for integrating these sports analytics functions?

Users require a foundational understanding of statistical regression, specifically logistic or isotonic calibration, and familiarity with sports data structures. Accessing the data requires a valid connection to the PuckAPI endpoint to retrieve game schedules, player statistics, and real-time betting odds for model input.