pytorch-model-trainer
Pytorch Model Trainer - Auto-activating skill for ML Training. Triggers on: pytorch model trainer, pytorch model trainer Part of the ML Training skill category.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill pytorch-model-trainerOverall
score
19%
Does it follow best practices?
Validation for skill structure
Activation
7%This description is severely underdeveloped, consisting mostly of metadata-style labels rather than actionable content. It fails to describe any concrete capabilities, lacks natural trigger terms users would actually say, and provides no guidance on when Claude should select this skill. The repeated trigger term suggests a template that wasn't properly filled out.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Creates PyTorch training loops, configures optimizers and loss functions, implements data loaders, saves/loads model checkpoints, monitors training metrics'
Add a 'Use when...' clause with natural trigger terms like 'train a neural network', 'PyTorch training', 'deep learning model', 'training loop', 'model training', 'fine-tune a model'
Include file types or artifacts the skill works with, e.g., '.pt files', 'model weights', 'training scripts', 'dataset loading'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the domain ('ML Training', 'Pytorch Model Trainer') but provides no concrete actions. It doesn't describe what the skill actually does - no mention of training loops, data loading, model architecture, hyperparameter tuning, 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 explaining when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'pytorch model trainer' repeated twice. Missing natural variations users would say like 'train a model', 'neural network', 'deep learning', 'training loop', 'PyTorch', 'ML model', 'machine learning training', etc. | 1 / 3 |
Distinctiveness Conflict Risk | While 'PyTorch' provides some specificity that distinguishes it from general ML skills, the lack of detail about what training capabilities it offers means it could overlap with other ML/deep learning skills. The 'ML Training' category is broad. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%This skill is essentially a placeholder with no substantive content. It describes what a PyTorch model trainer skill would do in vague marketing language but provides zero actionable guidance, code examples, or concrete workflows. The content fails on all dimensions by explaining concepts abstractly rather than providing executable instructions.
Suggestions
Add concrete, executable PyTorch code examples for common training tasks (e.g., DataLoader setup, training loop, model checkpointing)
Define a clear multi-step workflow for model training with validation checkpoints (e.g., data validation -> training -> evaluation -> saving)
Include specific guidance on hyperparameter tuning approaches with actual code or configuration examples
Add references to separate files for advanced topics like distributed training, experiment tracking integration, or custom loss functions
| 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 no actionable information. | 1 / 3 |
Actionability | Contains zero concrete guidance - no code examples, no commands, no specific steps. The entire skill describes what it does in abstract terms rather than instructing how to do anything with PyTorch model training. | 1 / 3 |
Workflow Clarity | No workflow is defined at all. For ML training tasks that involve data preparation, model training, and hyperparameter tuning, there should be clear sequential steps with validation checkpoints, but none are provided. | 1 / 3 |
Progressive Disclosure | The content is a flat, uninformative structure with no references to detailed materials, no links to examples, API references, or advanced guides. It mentions capabilities without pointing to any actual implementation details. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
69%Validation — 11 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 11 / 16 Passed | |
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.