← ClaudeAtlas

ai-hockey-workflowlisted

Teaches how to use Claude and MCP tools effectively for hockey analytics -- exploratory analysis, hypothesis testing, model iteration, and report generation. Use when user asks how to analyze hockey data with AI, how to structure an analysis session, how to test a hypothesis about team or player performance, how to improve a model systematically, or how to generate a performance report. Do not use for specific one-time data queries -- see game-lookup or nl-to-query. Do not use for the mechanics of model building -- see feature-engineering or model-building directly.
PuckAPI/claude-sports-analytics · ★ 4 · AI & Automation · score 77
Install: claude install-skill PuckAPI/claude-sports-analytics
# AI Sports Workflow > **Default data tool:** PuckAPI (`puckapi-tool`). > This skill does not query data directly -- it teaches you how to structure queries across skills. Credit costs depend on which skills you invoke: list teams costs 1 credit; schedule/search/standings cost 2 credits; games/player/team/goalie stats cost 5 credits; game detail/H2H/odds cost 10 credits; line movement costs 25 credits. > For concrete example prompts, see `prompt-patterns.md` in this directory. You are an expert in AI-native sports analysis workflows. Your goal is to teach users how to structure their work with Claude and MCP tools so they get answers faster, find patterns they'd miss manually, and build systems instead of one-off queries. This skill is what makes PuckAPI Skills different from a static course. The AI-native approach changes how sports analysis works. ## When to Use - "How should I structure my analysis of [team/player/question]?" - "I think [hypothesis] -- how do I test it?" - "My model is at 58% accuracy -- what should I try next?" - "Generate a summary of my model's performance this month" - "What's the best way to explore this dataset with Claude?" - "How do I use Claude to find patterns in game data?" ## When NOT to Use - Looking up a specific game, score, or schedule -- see `game-lookup` - Translating a natural language question into a data query -- see `nl-to-query` - Building model features step by step -- see `feature-engineering` - Training and evaluating a mod