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
Quality
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 severely underdeveloped, essentially serving as a placeholder rather than a functional skill description. It provides no concrete actions, no meaningful trigger terms beyond the skill name, and no guidance on when to use it. The only slight positive is that 'model pruning' refers to a specific ML technique.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Applies structured and unstructured pruning to neural networks, analyzes layer sensitivity, generates pruning schedules, and validates model accuracy post-pruning.'
Include natural trigger terms users would say: 'Use when the user mentions model compression, reducing model size, weight pruning, sparsity, making models smaller, or deploying to edge devices.'
Add an explicit 'Use when...' clause that describes the scenarios triggering this skill, such as 'Use when optimizing neural networks for deployment, reducing inference costs, or preparing models for resource-constrained environments.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the skill ('Model Pruning Helper') without describing any concrete actions. There are no specific capabilities listed like 'prune layers', 'reduce model size', or 'analyze sparsity'. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and the 'when' clause is just the skill name repeated. There is no explicit guidance on when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The only trigger term listed is 'model pruning helper' repeated twice, which is the skill name itself rather than natural keywords users would say. Missing terms like 'compress model', 'reduce parameters', 'sparsity', 'weight pruning', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'model pruning' is somewhat specific to a particular ML technique, which provides some distinctiveness. However, the lack of detail means it could overlap with other ML optimization or 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 content is an empty template that provides no actual guidance on model pruning. It lacks any concrete techniques (magnitude pruning, structured vs unstructured, etc.), code examples, or workflows. The content would be identical if you replaced 'model pruning helper' with any other topic.
Suggestions
Add concrete code examples for common pruning techniques (e.g., magnitude pruning with PyTorch, TensorFlow Model Optimization Toolkit)
Define a clear workflow: select pruning strategy → apply pruning → evaluate accuracy drop → fine-tune if needed → export optimized model
Include specific pruning parameters and their tradeoffs (sparsity levels, structured vs unstructured, layer-wise vs global)
Remove generic boilerplate sections ('Capabilities', 'Example Triggers') and replace with actionable technical content
| 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 gives zero executable guidance on how to actually prune models. | 1 / 3 |
Workflow Clarity | No workflow is defined. There are no steps, no sequence, and no validation checkpoints for what is inherently a multi-step technical process (selecting pruning strategy, applying pruning, validating accuracy, etc.). | 1 / 3 |
Progressive Disclosure | The content is a flat, generic template with no references to detailed documentation, examples, or related files. There's no structure that would help navigate to actual pruning techniques or implementations. | 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.