roc-curve-plotter

Roc Curve Plotter - Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter Part of the ML Training skill category.

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill roc-curve-plotter

What are skills?

1.04x

Quality

11%

Does it follow best practices?

Impact

94%

1.04x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/roc-curve-plotter/SKILL.md

SKILL.md

Review

Evals

Evaluation results

100%

10%

Credit Default Prediction: Model Evaluation

sklearn ROC curve computation

Criteria

Without context

With context

Uses sklearn roc_curve

100%

Uses sklearn AUC metric

100%

Uses pip for installs

100%

Python implementation

100%

ROC plot saved

100%

AUC in results.txt

100%

Production code structure

100%

AUC value reasonable

100%

Without context: $0.2164 · 1m 3s · 16 turns · 16 in / 2,760 out tokens

With context: $0.4865 · 1m 42s · 29 turns · 28 in / 5,300 out tokens

90%

Disease Diagnosis: Comparing Classifiers for Medical Screening

Multi-model ROC comparison pipeline

Criteria

Without context

With context

sklearn roc_curve used

100%

sklearn AUC metric

100%

sklearn classifiers

100%

Python script produced

100%

pip used for installs

100%

Production code quality

Comparison plot saved

100%

Report contains AUC values

100%

AUC values reasonable

100%

Without context: $0.2550 · 1m 7s · 17 turns · 18 in / 3,335 out tokens

With context: $0.4458 · 1m 38s · 27 turns · 27 in / 5,106 out tokens

92%

Customer Churn Prediction: Full ML Training Pipeline

End-to-end ML training and evaluation

Criteria

Without context

With context

sklearn roc_curve

100%

sklearn AUC metric

100%

Data preparation step

100%

Hyperparameter exploration

100%

Experiment tracking

100%

Best model ROC plot

100%

Python implementation

100%

pip used for installs

100%

Production code structure

20%

AUC value in valid range

100%

Without context: $0.4630 · 1m 47s · 26 turns · 68 in / 5,681 out tokens

With context: $0.5693 · 2m 7s · 32 turns · 64 in / 6,701 out tokens

Evaluated: 6 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Credit Default Prediction: Model Evaluation Disease Diagnosis: Comparing Classifiers for Medical Screening Customer Churn Prediction: Full ML Training Pipeline

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.