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
Quality
3%
Does it follow best practices?
Impact
100%
1.56xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/tensorflow-model-trainer/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is severely underdeveloped and would be nearly useless for skill selection. It provides no concrete actions, repeats the same trigger term twice, lacks any 'Use when' guidance, and relies entirely on the skill name rather than describing actual capabilities. The only slight positive is mentioning TensorFlow specifically.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Builds, trains, and evaluates TensorFlow/Keras neural network models. Handles data preprocessing, model architecture definition, training loops, and checkpoint saving.'
Add a 'Use when...' clause with natural trigger terms: 'Use when the user mentions TensorFlow, Keras, neural networks, deep learning training, model fitting, or needs to train ML models with GPU support.'
Include common file types and user phrases: '.h5 files', 'model checkpoints', 'training epochs', 'loss functions', 'train a model', 'fit the network'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the domain ('ML Training', 'Tensorflow Model Trainer') but provides no concrete actions. It doesn't describe what the skill actually does - no mention of training workflows, model architectures, data handling, or any specific capabilities. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the vague 'ML Training' category label. There is no 'Use when...' clause or explicit trigger guidance - only a redundant trigger phrase that doesn't help Claude understand when to select this skill. | 1 / 3 |
Trigger Term Quality | The triggers listed are just the skill name repeated twice ('tensorflow model trainer, tensorflow model trainer'). Missing natural user terms like 'train neural network', 'deep learning', 'model training', 'TensorFlow', 'fit model', 'epochs', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'Tensorflow' provides some specificity that distinguishes it from generic ML skills, but 'ML Training' is broad enough to potentially conflict with PyTorch, scikit-learn, or other ML framework skills. The lack of specific use cases increases conflict risk. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an empty placeholder template with no actual TensorFlow training content. It contains only generic boilerplate describing what a skill should do without providing any concrete guidance, code examples, or workflows for model training. The content would be completely useless for actually training TensorFlow models.
Suggestions
Add executable TensorFlow code examples showing model definition, compilation, and training (e.g., `model.fit()` with actual parameters)
Define a clear workflow: data loading → preprocessing → model architecture → training → evaluation → saving, with validation checkpoints
Include specific TensorFlow patterns like callbacks for checkpointing, TensorBoard integration, and learning rate scheduling
Replace generic capability claims with concrete guidance on hyperparameter tuning, distributed training, or mixed precision training
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic boilerplate that explains nothing Claude doesn't already know. Phrases like 'provides automated assistance' and 'follows industry best practices' are meaningless filler with zero actionable information. | 1 / 3 |
Actionability | There is no concrete code, no TensorFlow examples, no commands, no specific guidance whatsoever. The entire skill describes what it claims to do rather than providing any executable instructions for training models. | 1 / 3 |
Workflow Clarity | No workflow is defined. For a model training skill, there should be clear steps for data preparation, model definition, training loops, checkpointing, and evaluation - none of which are present. | 1 / 3 |
Progressive Disclosure | The content is a flat, generic template with no structure pointing to detailed resources. There are no references to examples, API documentation, or advanced topics - just empty marketing-style sections. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
0ad6004
- Reviewed
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.