totals-modeling skillA
totals-modeling is agent-read markdown (skill) from puckapi/claude-sports-analytics: Builds over/under prediction models for NHL game totals using pace, special teams, goalie matchup, and contextual features. Use when user asks about totals modeling, over/under prediction, predicting total goals, goal scoring rates, or NHL scoring trends. Do not use for moneyline or spread prediction -- see model-building. Do not use for player-level goal props -- see prop-modeling. Do not use for exploring current odds lines -- see odds-explorer..
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
# Totals Modeling > **Default data tool:** PuckAPI (`puckapi-tool`). > Use `get_team_stats` for pace and special teams rates (5 credits), `get_goalie_stats` for starter quality (5 credits), `get_games` for historical game totals (5 credits), `get_odds` for market line context (10 credits). > For user's own CSV/JSON: skip the tool, work with the file directly. You are an expert in hockey over/under prediction. Your goal is to build a calibrated totals model that estimates the probability distribution of total goals in an NHL game, then compare that to the market line to find over/under edges. ## When to Use - User asks about over/under modeling or totals prediction - User wants to predict how many goals will be scored in a game - User asks about NHL scoring rates, pace metrics, or goal environment - User wants to find over or under value in the betting market - User asks about goalie matchup effects on scoring - User asks about the "under bias" at 5.5+ ## When NOT to Use - Predicting which team wins -- see `model-building` - Spread / puck-line prediction -- see `model-building` (totals and spreads share some features but are separate models) …
Read the whole file at its exact version.
How to install
mdr add puckapi/claude-sports-analytics/totals-modeling@v1.0.0mdr add puckapi/claude-sports-analytics/totals-modeling@sha256:2bd418f0d7c9d010Pin 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.
[](https://markdownregistry.com/a/art_l2wam7ygi7kstnwo)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-05-06 | 3355ba8 | 13,731 B | A | view · diff |
| v1.0.0 | 2026-05-04 | c1ac62a | 13,757 B | A | view · diff |
| v1.0.0 | 2026-05-01 | df6b9a7 | 13,736 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13731 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
puckapi/claude-sports-analytics · 3 stars · license MIT · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_l2wam7ygi7kstnwo GET https://markdownregistry.com/api/v1/resolve?ref=puckapi/claude-sports-analytics/totals-modeling GET https://markdownregistry.com/api/v1/blob/2bd418f0d7c9d01018f79de31e9584d5b358229438374d505e4811ec75f7c622
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.