model-export-helper
Model Export Helper - Auto-activating skill for ML Deployment. Triggers on: model export helper, model export helper Part of the ML Deployment skill category.
31
0%
Does it follow best practices?
Impact
83%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/model-export-helper/SKILL.mdQuality
Discovery
0%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 essentially a placeholder with no substantive content. It provides only the skill name repeated as a trigger term and a broad category label, failing to describe any concrete capabilities, use cases, or natural trigger terms. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Converts trained ML models to deployment formats such as ONNX, TensorFlow SavedModel, TorchScript, or PMML. Handles model optimization, quantization, and packaging for production environments.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about exporting, converting, or deploying machine learning models, mentions formats like ONNX or SavedModel, or needs to prepare a model for production inference.'
Remove the redundant duplicate trigger term and replace with varied natural language terms users would actually say, such as 'export model', 'convert model', 'model deployment', 'model serialization', 'production model'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Model Export Helper' is a name, not a description of capabilities. There is no indication of what specific tasks this skill performs (e.g., converting models, serializing weights, generating ONNX files). | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is meaningfully answered. The description only states the skill name, a redundant trigger, and a category label. There is no 'Use when...' clause or equivalent. | 1 / 3 |
Trigger Term Quality | The only trigger terms listed are 'model export helper' repeated twice, which is the skill's own name rather than natural keywords a user would say. Missing terms like 'export model', 'ONNX', 'SavedModel', 'model conversion', 'deploy model', 'serialize model', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could overlap with any ML-related skill. 'ML Deployment' is a broad category, and without specific actions or file types, there is no clear niche to distinguish it from other ML or deployment skills. | 1 / 3 |
Total | 4 / 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 with no substantive content. It contains only generic boilerplate text that repeats the skill name without providing any actual guidance on model export (e.g., ONNX, TorchScript, SavedModel, TFLite formats, conversion steps, validation). It fails on every dimension because it teaches Claude nothing actionable.
Suggestions
Add concrete, executable code examples for common model export workflows (e.g., exporting PyTorch models to ONNX, TensorFlow SavedModel to TFLite) with specific commands and validation steps.
Define a clear multi-step workflow with validation checkpoints, such as: train/load model → export to target format → validate exported model → test inference → optimize for deployment.
Remove all boilerplate sections (Purpose, When to Use, Example Triggers) that just repeat the skill name, and replace with lean, actionable content covering specific export formats, tools, and common pitfalls.
Add references to detailed guides for advanced topics (e.g., quantization, model optimization, serving framework integration) using progressive disclosure rather than trying to cover everything inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know, repeats 'model export helper' excessively, and provides zero domain-specific information. Every section restates the same vague concept without adding value. | 1 / 3 |
Actionability | There are no concrete code examples, commands, specific tools, export formats, or executable guidance of any kind. The content only describes what the skill could do in abstract terms without actually instructing how to do anything. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. Claims to provide 'step-by-step guidance' but none is actually present. 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 files, no structured navigation, and no meaningful content 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
3076d78
- 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.