early-stopping-callback

Early Stopping Callback - Auto-activating skill for ML Training. Triggers on: early stopping callback, early stopping callback Part of the ML Training skill category.

1.01x

Quality

Does it follow best practices?

Impact

99%

1.01x

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/early-stopping-callback/SKILL.md

Evaluation results

99%

Prevent Model Overfitting During Long Training Runs

PyTorch early stopping best practices

Criteria

Without context

With context

Patience parameter

100%

Monitored metric

100%

Best weights restoration

100%

Improvement detection

100%

Reusable class or callable

100%

Training loop integration

100%

Production-ready code quality

87%

Python implementation

100%

Requirements listed

100%

Integration documentation

100%

Without context: $0.5990 · 5m 26s · 33 turns · 32 in / 9,075 out tokens

With context: $0.8842 · 5s · 2 turns · 4 in / 148 out tokens

100%

Stabilize Training for a Text Classification Model

TensorFlow/Keras early stopping with best model restoration

Criteria

Without context

With context

EarlyStopping callback used

100%

Validation metric monitored

100%

restore_best_weights enabled

100%

Patience configured

100%

Callback passed to model.fit

100%

Validation data provided

100%

Best model saved

100%

Production-ready code

100%

Metric monitoring explained

100%

Patience rationale explained

100%

Without context: $0.4953 · 5m 24s · 28 turns · 28 in / 6,689 out tokens

With context: $0.5077 · 3m 19s · 29 turns · 100 in / 5,941 out tokens

100%

Optimize Gradient Boosting Training for a Fraud Detection Pipeline

sklearn-compatible early stopping with output validation

Criteria

Without context

With context

Early stopping configured

100%

Separate validation set

100%

Validation metric monitored

100%

Stopping rounds/patience set

100%

Train/validation/test split

100%

Iteration-level logging

100%

Best iteration reported

100%

Output validated

100%

Production-ready Python

70%

100%

Common standards adherence

100%

Without context: $0.2844 · 1m 40s · 19 turns · 19 in / 4,509 out tokens

With context: $0.5501 · 2m 15s · 29 turns · 367 in / 7,334 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 994edc4

Evaluated: 18 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Prevent Model Overfitting During Long Training Runs Stabilize Training for a Text Classification Model Optimize Gradient Boosting Training for a Fraud Detection 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.