CtrlK
BlogDocsLog inGet started
Tessl Logo

tensorflow-model-trainer

Tensorflow Model Trainer - Auto-activating skill for ML Training. Triggers on: tensorflow model trainer, tensorflow model trainer Part of the ML Training skill category.

36

1.56x

Quality

3%

Does it follow best practices?

Impact

100%

1.56x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/tensorflow-model-trainer/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

46%

Flower Species Classifier

TensorFlow data prep and model training pipeline

Criteria
Without context
With context

Uses TensorFlow

0%

100%

Data preparation step

100%

100%

Train/test split

100%

100%

Model definition

0%

100%

Model compilation

0%

100%

Model training call

100%

100%

Model saved to disk

50%

100%

Evaluation metrics reported

100%

100%

Model architecture in report

40%

100%

Script is self-contained

100%

100%

Without context: $0.4597 · 1m 38s · 21 turns · 22 in / 6,594 out tokens

With context: $0.8713 · 3m 39s · 34 turns · 67 in / 9,296 out tokens

100%

12%

Sales Prediction Model Tuning

Hyperparameter tuning with experiment tracking

Criteria
Without context
With context

Uses TensorFlow

0%

100%

Multiple hyperparameter configs

100%

100%

Learning rate variation

100%

100%

Architecture variation

100%

100%

Validation split used

100%

100%

Results CSV produced

100%

100%

Best config JSON produced

100%

100%

Best config identified correctly

100%

100%

Data preparation in script

100%

100%

Reproducibility seed

100%

100%

Without context: $1.3017 · 3s · 1 turns · 3 in / 69 out tokens

With context: $1.1857 · 3s · 1 turns · 3 in / 120 out tokens

100%

49%

Heart Disease Risk Model: Training with Monitoring

Experiment tracking and production model saving

Criteria
Without context
With context

Uses TensorFlow

0%

100%

Data preparation

100%

100%

Train/validation/test split

100%

100%

TensorFlow model built

0%

100%

Model compiled correctly

0%

100%

Training history captured

40%

100%

training_history.json produced

100%

100%

Model saved to disk

50%

100%

Evaluation report produced

100%

100%

Validation during training

33%

100%

Without context: $0.3628 · 2m 1s · 18 turns · 20 in / 6,195 out tokens

With context: $1.9846 · 1s · 1 turns · 3 in / 23 out tokens

Repository
jeremylongshore/claude-code-plugins-plus-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.