cross-validation-setup

Cross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation setup, cross validation setup Part of the ML Training skill category.

0.92x

Quality

Does it follow best practices?

Impact

89%

0.92x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/cross-validation-setup/SKILL.md

Evaluation results

83%

-17%

Classifier Benchmarking Pipeline

K-fold cross-validation setup with sklearn

Criteria

Without context

With context

Uses sklearn CV

100%

sklearn or compatible framework

100%

Mean and std reported

100%

53%

Multiple classifiers

100%

Reusable functions

100%

No data leakage

100%

results.txt produced

100%

Pip for dependencies

100%

Stratified or appropriate split

100%

85%

-5%

Automated Hyperparameter Optimization for a Production Model

Hyperparameter tuning with cross-validated search

Criteria

Without context

With context

CV-based search utility

100%

sklearn framework

100%

Mean CV score reported

100%

search_results.csv produced

100%

run_log.txt produced

100%

Reusable structure

100%

No data leakage

100%

Meaningful param space

100%

Pip for install

100%

CV folds specified

100%

End-to-End ML Training Pipeline with Experiment Tracking

Full ML training workflow with CV and experiment tracking

Criteria

Without context

With context

K-fold loop implemented

100%

sklearn/pytorch/tensorflow used

100%

Per-fold data preparation

100%

Per-fold metric recording

100%

Mean and std in summary

100%

fold_metrics.csv produced

100%

experiment_summary.json produced

100%

Reusable code structure

100%

Pip for dependencies

100%

Full workflow coverage

100%

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3076d78

Evaluated: about 2 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Classifier Benchmarking Pipeline Automated Hyperparameter Optimization for a Production Model End-to-End ML Training Pipeline with Experiment Tracking

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.