agentleFS
PuckAPIPuckAPI/claude-sports-analytics/CLAUDE.md

claude-sports-analytics

CLAUDE.md3 starsChanged 18 days agoMITView on GitHub

This is a public, open-source repository. Every commit, file, and message is visible to anyone. - 28 skills, all NHL/hockey focused - MCP server at mcp.puckapi.com/mcp - Data starts from the 2010-11 season. 16 completed seasons plus the one in progress. Do not claim 2008-09; it is not there - 32 active NHL teams (includes Utah Hockey Club, not Arizona Coyotes) - Odds from the books PuckAPI tracks (DraftKings, FanDuel, BetMGM, ESPN BET and others). The count moves as books…

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep them concise and professional

    line 19
  2. Distinctive:

    No comments referencing internal conversations or decisions

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Hockey Skills -- Claude Code Instructions

Public Repo Rules

This is a public, open-source repository. Every commit, file, and message is visible to anyone.

Never include:

  • AI attribution or co-author lines in commits, code, or comments
  • Personal information (names, emails, addresses, usernames beyond the org)
  • API keys, secrets, tokens, or credentials (even expired ones)
  • Internal URLs, private repo paths, or filesystem paths (e.g., /Users/*)
  • References to private repos, internal tools, or business strategy
  • Revenue numbers, pricing strategy discussions, or customer data
  • References to other projects (PuckCast, OWSH, brain vault, etc.)

Commit messages:

  • Written as if by the project maintainer, not an AI
  • Describe the what and why, no "Generated by" or "Co-Authored-By" lines
  • Keep them concise and professional

Code and content:

  • No "AI-powered", "intelligent", or similar buzzwords
  • No comments referencing internal conversations or decisions
  • Skill descriptions should be factual and specific to what the skill does
  • Credit costs must match the live PuckAPI pricing (see puckapi-tool/endpoints.md)

Repo Structure

claude-sports-analytics/
├── .claude-plugin/plugin.json   # Plugin manifest
├── skills/                      # 28 skill directories
│   ├── puckapi-tool/            # MCP tool reference (endpoints + fields)
│   ├── hockey-analytics/        # Core metrics and concepts
│   ├── game-lookup/             # Finding and filtering games
│   └── ...                      # See README for full list
└── docs/                        # Glossaries, routing, season logic

Key Facts

  • 28 skills, all NHL/hockey focused
  • MCP server at mcp.puckapi.com/mcp
  • Data starts from the 2010-11 season. 16 completed seasons plus the one in progress. Do not claim 2008-09; it is not there
  • 32 active NHL teams (includes Utah Hockey Club, not Arizona Coyotes)
  • Odds from the books PuckAPI tracks (DraftKings, FanDuel, BetMGM, ESPN BET and others). The count moves as books come and go, so do not publish a number.
  • 15 MCP tools with credit costs defined in puckapi-tool/endpoints.md
  • Shot-quality metrics are returned by the API, not computed by the caller: gsax, expectedGoalsAgainst, highDangerSavePct, rollingSavePct, rollingGsax, trend, restDays on goalies; corsiPct, fenwickPct, expectedGoalsFor, expectedGoalsAgainst on teams; goalie_starts with time on ice on get_game_detail
  • Team possession is 5v5 by convention, goalie expected goals cover every strength. Never difference the two

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.