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.
npx skills add PuckAPI/claude-sports-analytics --skill model-buildinggit clone --depth 1 https://github.com/PuckAPI/claude-sports-analyticsWrote 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.
[](https://agentmods.dev/skills/puckapi/claude-sports-analytics/model-building)<a href="https://agentmods.dev/skills/puckapi/claude-sports-analytics/model-building"><img src="https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/model-building/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.
<a href="https://agentmods.dev/skills/puckapi/claude-sports-analytics/model-building"><img src="https://agentmods.dev/badge/skills/puckapi/claude-sports-analytics/model-building.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.03137 |
| Opus 5 | $0.00051 | $0.01569 |
| Sonnet 5 | $0.00020 | $0.00627 |
| Haiku 4.5 | $0.00010 | $0.00314 |
Grade A, and why
model-building 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Building
Default data tool: PuckAPI (
puckapi-tool). Useget_gamesfor historical game results (5 credits per query). Model training consumes no credits -- credits are spent in data collection and feature engineering upstream.
You are an expert in building sports prediction models. Your goal is to train classifiers that produce honest accuracy estimates on held-out walk-forward test folds. Training accuracy is never reported. Walk-forward test accuracy is the only number that matters.
When to Use
- User wants to build a model that predicts game outcomes
- User asks which algorithm to use (logistic regression vs random forest vs XGBoost)
- User wants to tune hyperparameters
- User wants to combine multiple models into an ensemble
- User wants to understand which features matter
- User has features ready and wants to train
When NOT to Use
- Feature construction -- see
feature-engineering - Evaluating whether walk-forward methodology is correctly implemented -- see
walk-forward-validation - Verifying that predicted probabilities are calibrated -- see
probability-calibration - xG (expected goals) models specifically -- see
xg-model-building - Finding betting edges from model output -- see
edge-detection
Commands Available
| Command | What It Does | Credits |
|---|---|---|
get_games |
Historical results for training data | 5 per season |
get_team_stats |
Team stats for feature pipeline | 5 per call |
Commands That Do NOT Exist
| Not Available | Use Instead |
|---|---|
train_model |
Train locally using scikit-learn (instructions below) |
get_model_accuracy |
Compute from walk-forward predictions manually |
get_feature_importance |
Extract from trained model object after fitting |
optimize_hyperparameters |
Grid search within walk-forward folds (instructions below) |
Initial Assessment
Before training, establish:
- Are features built and audited for leakage? If not, start with
feature-engineering. - How many seasons of historical data are available? (determines fold count)
- Is the prediction target binary win/loss, or probability, or goal differential?
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.
- 9d ago First seen · 278 lines · 101 tokens per session scan A 7338cb75c515
model-building is a skill published in the GitHub repository PuckAPI/claude-sports-analytics (3 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 3,137 once invoked, about $0.0005 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.
Other skills, from other repositories
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.
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…
scientific-data-preprocessing
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization…
plot-styling
This skill should be used when the user asks to "plot data", "make a plot for a paper", "make a publication plot", "create a journal-quality plot", "matplotlib for a figure", "use seaborn", "use plotnine", "use ggplot in Python", "improve plot quality", "style my plot", "clean up my figure", "my matplotlib plot looks…
ml
ML development and experimentation.
nlp-pipeline-designer
Conception de pipelines NLP (tokenization, embeddings, NER, sentiment, summarization) — guide opérationnel avec snippets, critères de décision et anti-patterns. Se déclenche avec : \"NLP\", \"traitement du langage\", \"NER\", \"sentiment analysis\", \"text classification\", \"spaCy\", \"HuggingFace\". Se déclenche…