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 description is extremely thin—it essentially restates the skill name and category without describing any concrete capabilities, use cases, or meaningful trigger terms. It would be nearly impossible for Claude to confidently select this skill over others in a large skill library, and the duplicated trigger term suggests auto-generated boilerplate rather than thoughtful authoring.
Suggestions
Add specific concrete actions such as 'Converts PyTorch, TensorFlow, or Keras models to ONNX format, validates ONNX graph structure, and optimizes models for inference deployment.'
Include a 'Use when...' clause with natural trigger scenarios, e.g., 'Use when the user asks to export a model to ONNX, convert between ML frameworks, or prepare a model for ONNX Runtime deployment.'
Expand trigger terms to cover natural user language variations: 'onnx export', 'convert model to onnx', 'pytorch to onnx', 'model serialization', '.onnx file', 'onnx runtime'.
| 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 'what' is essentially absent beyond the name, and the 'when' is only a redundant trigger term with no explicit 'Use when...' clause describing scenarios or user intents that should activate this skill. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'onnx converter' repeated twice. It misses natural variations users would say like 'convert model to onnx', 'export onnx', 'model conversion', '.onnx', 'onnx export', 'pytorch to onnx', 'tensorflow to onnx'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'ONNX' does narrow the domain somewhat compared to a fully generic description, but the vague 'ML Deployment' category and lack of specific actions 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 instructional content. It consists entirely of boilerplate meta-descriptions about what the skill supposedly does, without providing any concrete ONNX conversion guidance, code, commands, or workflows. It would be completely unhelpful to Claude in performing any ONNX-related task.
Suggestions
Add concrete, executable code examples showing how to convert models from common frameworks (PyTorch, TensorFlow) to ONNX format, e.g., `torch.onnx.export()` with specific parameters.
Define a clear multi-step workflow: export model → validate ONNX graph (`onnx.checker.check_model`) → optimize (`onnxoptimizer`) → test inference with ONNX Runtime, including validation checkpoints.
Remove all meta-description sections ('Purpose', 'When to Use', 'Example Triggers', 'Capabilities') that describe the skill rather than teaching the task, and replace with actionable content.
Include common pitfalls and troubleshooting guidance, such as handling dynamic axes, unsupported operators, and opset version selection.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler with no substantive information. It explains what the skill does in vague, generic terms without providing any actual ONNX conversion knowledge, commands, or code. Every section restates the same idea in different words. | 1 / 3 |
Actionability | There is zero concrete, executable guidance. No code examples, no specific commands, no library references, no conversion steps. Phrases like 'Provides step-by-step guidance' and 'Generates production-ready code' describe capabilities without demonstrating any. | 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 | The content is a flat, repetitive structure with no references to external files, no organized sections of real content, and no navigation to deeper materials. The sections that exist are all meta-description 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
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.