onnx-converter
Onnx Converter - Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of the ML Deployment skill category.
35
3%
Does it follow best practices?
Impact
94%
1.02xAverage 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/onnx-converter/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 is a very weak skill description that essentially just restates the skill name and category without providing any concrete actions, use cases, or meaningful trigger terms. It reads like auto-generated boilerplate rather than a useful description for skill selection. The duplicate trigger term and absence of a 'Use when...' clause make it nearly useless for distinguishing this skill from others.
Suggestions
Add specific concrete actions such as 'Converts PyTorch, TensorFlow, or Keras models to ONNX format, validates ONNX model graphs, and optimizes models for inference deployment.'
Add an explicit 'Use when...' clause with natural trigger terms like 'Use when the user asks to convert a model to ONNX, export a neural network for deployment, or mentions .onnx files, model serialization, or cross-framework model portability.'
Remove the duplicate trigger term and expand with natural variations users would say: 'onnx export', 'convert to onnx', 'model conversion', 'pytorch to onnx', 'onnx optimization'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the tool ('Onnx Converter') and a vague category ('ML Deployment') but lists no concrete actions like 'converts PyTorch models to ONNX format', 'exports TensorFlow graphs', or 'validates ONNX model compatibility'. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond restating the name, and has no explicit 'when should Claude use it' clause. The 'Triggers on' line is just a repeated keyword, not meaningful guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'onnx converter' repeated twice. Missing natural variations users would say like 'convert model to onnx', 'export onnx', 'model conversion', '.onnx', 'pytorch to onnx', 'tensorflow to onnx', or 'model deployment'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'ONNX' does provide some niche specificity that distinguishes it from generic ML or document skills, but the lack of concrete actions and the broad 'ML Deployment' category could cause overlap with other model conversion 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 is an empty shell with no actual content about ONNX conversion. It contains only generic boilerplate descriptions of what the skill supposedly does without any concrete guidance, code examples, commands, or workflows. It provides zero value beyond what Claude already knows about ONNX conversion.
Suggestions
Add executable code examples showing how to convert models from common frameworks (PyTorch, TensorFlow) to ONNX format, e.g., `torch.onnx.export()` with specific parameters.
Include a clear multi-step workflow: export model → validate with `onnx.checker.check_model()` → optimize with `onnxoptimizer` → test inference with ONNX Runtime, with validation at each step.
Add concrete guidance on common pitfalls like dynamic axes, opset version selection, and operator compatibility, with specific solutions.
Remove all generic boilerplate sections (Purpose, When to Use, Capabilities, Example Triggers) and replace with actionable technical content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler with no substantive information. It explains nothing Claude doesn't already know and provides zero actual guidance on ONNX conversion. Every section is generic boilerplate that could apply to any skill. | 1 / 3 |
Actionability | There are no concrete code examples, commands, or specific instructions for ONNX conversion. The content is entirely abstract and descriptive—phrases like 'provides step-by-step guidance' without actually providing any steps. | 1 / 3 |
Workflow Clarity | No workflow is defined at all. There are no steps, no sequence, no validation checkpoints. The skill claims to provide 'step-by-step guidance' but contains none. | 1 / 3 |
Progressive Disclosure | There are no references to external files, no structured navigation, and no meaningful content organization. The sections that exist are all superficial metadata rather than instructional content. | 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.