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.
21
3%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/model-pruning-helper/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 extremely weak across all dimensions. It is essentially a template-generated stub that names a domain ('model pruning') and a category ('ML Deployment') but provides no concrete actions, no meaningful trigger terms, and no explicit guidance on when Claude should select this skill. It would be nearly indistinguishable from any other auto-generated ML skill stub.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Applies structured and unstructured pruning to neural network models, analyzes layer-wise sparsity, evaluates accuracy-compression tradeoffs, and exports pruned models for deployment.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about pruning a model, reducing model size, weight sparsity, compressing neural networks, or optimizing models for edge deployment.'
Remove the redundant duplicate trigger term and replace with diverse natural language variations users would actually say, such as 'prune layers', 'sparse model', 'model compression', 'reduce parameters'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain ('model pruning') but describes no concrete actions. There are no specific capabilities listed such as 'prune layers', 'analyze sparsity', or 'reduce model size'. It only states it is a 'helper' which is vague. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming the domain, and the 'when' clause is just a self-referential trigger ('triggers on: model pruning helper'). There is no explicit 'Use when...' guidance with meaningful context. | 1 / 3 |
Trigger Term Quality | The only trigger term is 'model pruning helper' repeated twice. It lacks natural variations users might say such as 'prune model', 'reduce model size', 'sparsity', 'weight pruning', 'structured pruning', 'compress model', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'model pruning' is fairly specific to a niche ML task, which provides some distinctiveness. However, the lack of concrete actions and the generic 'ML Deployment' category could cause overlap with other ML deployment skills. | 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 shell with no substantive content. It consists entirely of generic boilerplate that could apply to any topic, with the phrase 'model pruning helper' substituted in. It provides zero actionable information about model pruning techniques, tools, or workflows.
Suggestions
Add concrete, executable code examples for common pruning techniques (e.g., magnitude pruning with PyTorch's torch.nn.utils.prune, structured pruning, knowledge distillation) with specific parameters and expected outputs.
Define a clear multi-step workflow: select pruning strategy → apply pruning → evaluate accuracy/latency tradeoff → validate model → export for deployment, with explicit validation checkpoints at each stage.
Replace all generic boilerplate sections (Purpose, When to Use, Capabilities, Example Triggers) with actual technical content: supported frameworks, pruning ratio guidelines, sparsity targets, and common pitfalls.
Add references to advanced topics in separate files (e.g., STRUCTURED_PRUNING.md, QUANTIZATION_AWARE.md) for progressive disclosure of complex pruning strategies.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know, repeats 'model pruning helper' excessively, and provides zero actual pruning-specific information. Every section is generic padding. | 1 / 3 |
Actionability | There is no concrete guidance whatsoever—no code, no commands, no specific techniques, no libraries, no parameters. The skill describes what it claims to do rather than actually instructing how to do anything. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. The bullet 'Provides step-by-step guidance' is a meta-claim with no actual steps. There are no validation checkpoints or sequenced operations. | 1 / 3 |
Progressive Disclosure | The content is a flat, monolithic block of generic text with no references to detailed materials, no links to examples or advanced guides, and no meaningful structural organization beyond boilerplate headings. | 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
87f14eb
- 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.