Home / puckapi / claude-sports-analytics · skills/nl-to-query/SKILL.md · GitHub

nl-to-query skillA

nl-to-query is agent-read markdown (skill) from puckapi/claude-sports-analytics: Translates natural language hockey queries into structured data filters and executes them via puckapi-tool. Use when user asks a research question in plain English: 'show me games where the home team was outshot but won', 'find all back-to-back losses', 'how often do goalies with 2 days rest outperform their season SV%'. Includes a self-correction loop -- retries with adjusted parameters if the first query returns unexpected results. Do not use for specific known queries where the right tool is .

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# NL to Query

> **Default data tool:** PuckAPI (`puckapi-tool`).
> Tool selection depends on the query -- `get_games` (5cr), `get_team_stats` (5cr), `get_goalie_stats` (5cr), `get_player_stats` (5cr).
> For odds queries, note `get_odds` costs 10 credits per game.

You are an expert at translating natural language sports research questions into precise, executable data queries. Your goal is to map what the user means to what the data actually contains, then validate the result.

## When to Use

- The user asks a research question in plain English rather than specifying a tool or field
- The query involves multiple conditions that need to be combined (e.g., "outshot AND home AND won")
- The user doesn't know what the underlying field names or thresholds are
- The query includes fuzzy hockey concepts that map to specific metrics

## When NOT to Use

- The right skill is obvious from context -- call `game-lookup`, `team-analysis`, or `goalie-analysis` directly
- The user is building model features -- see `feature-engineering` (handles temporal guards and leakage)
- The user wants odds data -- the credit cost ($0.10/game) should be flagged before running at scale
…

Read the whole file at its exact version.

How to install

Latest version
mdr add puckapi/claude-sports-analytics/nl-to-query@v1.0.0
Exact content
mdr add puckapi/claude-sports-analytics/nl-to-query@sha256:73b2a03cd69e5e34

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pxj2ffuzy5k7qfoj.svg)](https://markdownregistry.com/a/art_pxj2ffuzy5k7qfoj)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.0.0 latest2026-05-06 9b33f46 8,918 BA view · diff
v1.0.02026-05-06 3355ba8 8,918 BA view · diff
v1.0.02026-05-04 c1ac62a 8,980 BA view · diff
v1.0.02026-05-01 df6b9a7 8,967 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8918 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

puckapi/claude-sports-analytics · 3 stars · license MIT · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pxj2ffuzy5k7qfoj
GET https://markdownregistry.com/api/v1/resolve?ref=puckapi/claude-sports-analytics/nl-to-query
GET https://markdownregistry.com/api/v1/blob/73b2a03cd69e5e34cb303e0539f52e799ed1df3667ba892c203e51b0225c43a6

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from puckapi/claude-sports-analytics

CLAUDE.md claude
puckapi/claude-sports-analytics · CLAUDE.md
git:20260921.dcae9a3 · audit A · 3 stars
ai-hockey-workflow skill
puckapi/claude-sports-analytics · skills/ai-hockey-workflow/SKILL.md · Teaches how to use Claude and MCP tools effectively for hockey analytics -- exploratory analysis, hypothesis testing…
v1.0.0 · audit A · 3 stars
backtesting skill
puckapi/claude-sports-analytics · skills/backtesting/SKILL.md · Walk-forward historical testing of betting strategies to determine whether a model's edge is real. Use when user asks…
v1.0.0 · audit A · 3 stars
bet-tracker skill
puckapi/claude-sports-analytics · skills/bet-tracker/SKILL.md · Track predictions vs actuals in production: log bets, compute CLV, monitor ROI, detect edge decay, and run significance…
v1.0.0 · audit A · 3 stars
daily-card skill
puckapi/claude-sports-analytics · skills/daily-card/SKILL.md · Full slate analysis for tonight's games with edge rankings, odds across books, and recommended stakes. Use when user…
v1.0.0 · audit A · 3 stars
data-pipeline skill
puckapi/claude-sports-analytics · skills/data-pipeline/SKILL.md · Builds automated sports analytics pipelines -- daily data pulls, scheduled prediction generation, model versioning…
v1.0.0 · audit A · 3 stars
dispatch skill
puckapi/claude-sports-analytics · skills/dispatch/SKILL.md · Routes hockey analytics requests to the right 2-3 skills. Load this FIRST when a hockey data or analytics request comes…
v1.0.0 · audit A · 3 stars
edge-detection skill
puckapi/claude-sports-analytics · skills/edge-detection/SKILL.md · Compares model probabilities against market odds to find positive expected value bets. Use when user asks about EV…
v1.0.0 · audit A · 3 stars
elo-engineering skill
puckapi/claude-sports-analytics · skills/elo-engineering/SKILL.md · Builds multi-variant Elo rating systems for sports prediction. Use when user asks about Elo ratings, rating systems…
v1.0.0 · audit A · 3 stars
feature-engineering skill
puckapi/claude-sports-analytics · skills/feature-engineering/SKILL.md · Transforms raw game, player, and goalie data into model-ready features with built-in leakage detection. Use when user…
v1.0.0 · audit A · 3 stars
game-lookup skill
puckapi/claude-sports-analytics · skills/game-lookup/SKILL.md · Finds games by date, team, matchup, or season -- past results, tonight's slate, upcoming schedule, head-to-head…
v1.0.0 · audit A · 3 stars
game-preview skill
puckapi/claude-sports-analytics · skills/game-preview/SKILL.md · Complete pre-game analysis for a single NHL (or other sport) matchup: team records, goalie matchup, key stats, odds…
v1.0.0 · audit A · 3 stars

Every file in puckapi/claude-sports-analytics

Browse by kind, by grade A, or by owner.