skills.rest
PuckAPI
PuckAPIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

xg-model-building

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

2|1|Updated May 1, 2026
Search Tags:#play-by-play#model building#nhl#xg#expected goals#shot data#hockey analytics
One-click install
npx skills add https://github.com/PuckAPI/claude-sports-analytics --skill xg-model-building
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: xg-model-building
Source: https://github.com/PuckAPI/claude-sports-analytics/tree/main/skills/xg-model-building
Command: npx skills add https://github.com/PuckAPI/claude-sports-analytics --skill xg-model-building

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps hockey analysts and data scientists develop models that estimate the probability of a shot resulting in a goal, enabling deeper tactical and player performance insights.

Core Features & Use Cases

  • Build shot-level xG models using NHL play-by-play data to quantify shot quality.
  • Predict goal probabilities based on shot location, type, strength state, and contextual features like rebounds and rushes.
  • Use Case: A user wants to analyze how different shot types and zones influence scoring chances, or validate team performance metrics like xGF%.

Quick Start

Describe to the AI: analyze NHL shot event data to generate a goal probability model considering shot location, type, and game context.

Frequently Asked Questions about xg-model-building

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an expected goals model using NHL play-by-play data?▼

Expected goals models work by analyzing NHL play-by-play data to calculate the probability of each shot becoming a goal. They evaluate shot location, type, strength state, and contextual factors like rebounds and rushes to quantify shot quality.

What features are most important for predicting NHL goal probabilities?▼

Key features for predicting NHL goal probabilities include shot location, shot type, strength state, and contextual factors like rebounds and rushes. These play-by-play data points drive accurate shot quality estimation.

Can I use NHL shot data to analyze team performance metrics like xGF%?▼

Yes, you can use NHL shot data to validate team performance metrics like xGF%. By generating shot-level expected goals probabilities, you can quantify scoring chances and evaluate overall team and player analytics.

Does this approach to hockey analytics require specific dependencies or environments?▼

No specific dependencies are required to start modeling expected goals. The Skill functions independently to process NHL shot event data, requiring only your play-by-play dataset to generate goal probability outputs.

What is the best way to quantify shot quality in hockey analytics?▼

The best way to quantify shot quality is developing a shot-level expected goals model. This predicts goal probabilities by analyzing NHL play-by-play shot data, including shot location, type, and game context.

Related Skills

Explore More Data & Analytics Skills→
sports-data-hqsports-data-hq
1

xg-model-building

Build expected goals models from NHL play-by-play shot events.

Official
Advanced
PuckAPIPuckAPI
2

hockey-analytics

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

Official
Intermediate
89jobrien89jobrien
4

machine-learning

Automate the machine learning lifecycle from experimentation to production deployment.

Community
Advanced
sports-data-hqsports-data-hq
1

totals-modeling

Build calibrated NHL totals prediction models for game goal distributions and over/under probabilities.

Official
Advanced