model-pruning-helper
Model Pruning Helper - Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model pruning helper Part of the ML Deployment skill category.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill model-pruning-helperOverall
score
19%
Does it follow best practices?
Validation for skill structure
Activation
7%This description is severely underdeveloped, consisting only of boilerplate metadata without any substantive content. It fails to explain what model pruning capabilities are offered, what specific actions Claude can perform, or when this skill should be selected. The repeated trigger term and lack of natural user language make it nearly useless for skill selection.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Applies structured and unstructured pruning to neural networks, analyzes weight importance, generates pruning schedules, and evaluates accuracy-sparsity tradeoffs.'
Include a 'Use when...' clause with natural trigger terms like 'reduce model size', 'compress neural network', 'remove redundant weights', 'sparsity', 'smaller model for deployment'.
Differentiate from related ML optimization skills by specifying the pruning techniques supported (magnitude pruning, lottery ticket, etc.) and deployment contexts (edge devices, inference optimization).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions - only the name 'Model Pruning Helper' and category 'ML Deployment'. There are no specific capabilities listed like 'prune weights', 'reduce model size', or 'optimize inference'. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and provides no 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The only trigger terms listed are 'model pruning helper' repeated twice, which is the skill name itself rather than natural user language. Missing terms users would actually say like 'reduce model size', 'compress model', 'remove weights', 'sparsity'. | 1 / 3 |
Distinctiveness Conflict Risk | While 'model pruning' is a specific ML concept that wouldn't conflict with most skills, the lack of detail means it could overlap with other ML optimization skills (quantization, distillation, compression). The category mention provides some distinction. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%This skill is an empty template that provides zero actionable guidance on model pruning. It contains only generic placeholder text describing what a skill should do rather than actually teaching model pruning techniques, tools, or workflows. The content fails every dimension by being verbose filler with no concrete value.
Suggestions
Add concrete model pruning techniques with executable code examples (e.g., magnitude pruning, structured pruning using PyTorch or TensorFlow)
Include a clear workflow: analyze model -> select pruning strategy -> apply pruning -> validate accuracy -> export pruned model
Provide specific tool recommendations and code snippets (e.g., torch.nn.utils.prune, TensorFlow Model Optimization Toolkit)
Remove all generic boilerplate text and replace with actual pruning parameters, thresholds, and validation checkpoints
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic boilerplate that explains nothing specific about model pruning. Phrases like 'provides automated assistance' and 'follows industry best practices' are filler that Claude already understands. | 1 / 3 |
Actionability | No concrete code, commands, or specific techniques for model pruning are provided. The content describes what the skill does abstractly but never instructs how to actually prune a model. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. Claims to provide 'step-by-step guidance' but none is actually present in the content. | 1 / 3 |
Progressive Disclosure | No references to detailed documentation, no structured navigation, and no actual content to organize. The skill is a hollow template with no substance to disclose progressively. | 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.