ai-hockey-workflow

ai-hockey-workflow is a skill for Claude Code from PuckAPI/claude-sports-analytics. It costs 116 tokens per session (2,389 once invoked), scanned A, original, MIT.

A workflow guide for using Claude and external tools to analyze hockey data. It covers exploring data, testing ideas about team or player performance, improving models, and writing reports.

In plain words
What is it for?
Use it to plan hockey-data questions, test performance hypotheses, decide what to try when a model is inaccurate, and summarize results.
Why use it?
It gives structure to analysis sessions so you can investigate questions systematically instead of relying on one-off queries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the puckapi-skills plugin — 28 skills shipped together

Good fit Use it to plan hockey-data questions, test performance hypotheses, decide what to try when a model is inaccurate, and summarize results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/puckapi/claude-sports-analytics/ai-hockey-workflow
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add PuckAPI/claude-sports-analytics --skill ai-hockey-workflow
Clone the repo
git clone --depth 1 https://github.com/PuckAPI/claude-sports-analytics

Made for: Claude Code.

Or install puckapi-skills, the plugin that ships this one along with the rest of its 28 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-hockey-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/ai-hockey-workflow/github.svg)](https://agentmods.dev/skills/puckapi/claude-sports-analytics/ai-hockey-workflow)
Your own site
<a href="https://agentmods.dev/skills/puckapi/claude-sports-analytics/ai-hockey-workflow"><img src="https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/ai-hockey-workflow/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-hockey-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/puckapi/claude-sports-analytics/ai-hockey-workflow"><img src="https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/ai-hockey-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.02389
Opus 5 $0.00058 $0.01195
Sonnet 5 $0.00023 $0.00478
Haiku 4.5 $0.00012 $0.00239

Measured 11d ago against content hash 82f4bff38e85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-hockey-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai-hockey-workflow/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 model -- see model-building
  • Backtesting a strategy -- see backtesting

Commands Available

No direct data commands. This skill orchestrates other skills and teaches workflow patterns.

Pattern Skills Invoked Typical Credits
Exploratory analysis game-lookup, team-analysis, player-scouting 3-10
Hypothesis test team-analysis, game-lookup, compute in session 5-15
Model iteration feature-engineering, model-building, walk-forward-validation 5-20
Report generation bet-tracker, backtesting, visualization 5-25

Read the full file on GitHub · 213 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 213 lines · 116 tokens per session scan A 82f4bff38e85

Subscribe to this mod's changes

ai-hockey-workflow is a skill published in the GitHub repository PuckAPI/claude-sports-analytics (3 stars, last pushed 4mo ago), licensed MIT. It adds 116 tokens to every session and 2,389 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

scientific-slides

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…

foryourhealth111-pixel/Vibe-Skills · 65 tokens

LQF_Machine_Learning_Expert_Guide

LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…

foryourhealth111-pixel/Vibe-Skills · 152 tokens

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

foryourhealth111-pixel/Vibe-Skills · 62 tokens

paper-2-web

Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.

foryourhealth111-pixel/Vibe-Skills · 40 tokens

get-available-resources

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to…

foryourhealth111-pixel/Vibe-Skills · 115 tokens

plotly

Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly…

foryourhealth111-pixel/Vibe-Skills · 85 tokens