Learn hockey analytics, one diagram at a time.
Pick a pillar and work through its visual explainers. Start with foundations, build a real data stack, then layer AI and reusable skills on top.
Foundations
What hockey analytics actually is, how to read the game with data, and the metrics that matter.
ExploreData Stack
How to build a hockey data pipeline: sources, ingestion, storage, transforms and serving.
ExploreAI & Claude
Use LLMs and agents to analyze hockey: prompting, tool use, MCP and retrieval over your own data.
ExploreSkills
Reusable AI skills and playbooks: scouting reports, opponent prep, xG, dashboards — as repeatable procedures.
ExploreArchitectures
Reference architectures and data flows drawn as diagrams — the signature visual explainers.
ExploreWorkflows & Craft
How great analysts actually work: framing questions, validating, storytelling and shipping decisions.
ExploreNew to the metrics? Start with the hockey analytics glossary — plain-language definitions of xG, Corsi, Fenwick and more.
Latest explainers
Corsi vs Fenwick: which possession metric should you use?
Two shot-attempt metrics, one small difference — and when each one tells the truer story.
Getting started with DuckDB for hockey data
Why a single-file analytical database is the fastest way to start your hockey data stack.
What is MCP, and why it matters for hockey analytics
The open protocol that lets an AI safely query your data — explained in one diagram.
How a hockey analytics data stack works
The end-to-end path from raw game data to an answer you can act on — drawn as one diagram.
Using Claude to analyze your hockey data
How an LLM turns your data stack into a question-and-answer machine — safely.
What is expected goals (xG) in hockey?
The single most useful hockey metric, explained from shot to season total.
How to frame a hockey analytics question
The step great analysts never skip: turning a vague hunch into an answerable question.
Turn a prompt into a reusable AI skill
How to package a one-off AI request into a repeatable procedure your whole workflow can call.
A reference architecture for hockey analytics
A full, opinionated blueprint tying data, models, AI and delivery into one system.