onnx-converter

Onnx Converter - Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of the ML Deployment skill category.

1.02x

Quality

Does it follow best practices?

Impact

94%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/onnx-converter/SKILL.md

Evaluation results

98%

Deploy PyTorch Model to ONNX for Production Inference

PyTorch to ONNX export with validation

Criteria

Without context

With context

Uses torch.onnx.export

100%

Sets input/output names

100%

Dynamic axes configured

100%

Opset version specified

100%

Model in eval mode

100%

ONNX model validation

100%

Output comparison

100%

Step-by-step documentation

100%

Production inference example

100%

No training-mode export

60%

90%

Standardize ML Model Deployment Across Platforms

Scikit-learn pipeline ONNX conversion

Criteria

Without context

With context

Uses skl2onnx library

100%

Defines initial_type

100%

Correct input dtype

100%

Batched input shape

100%

ONNX model validation

ONNX Runtime inference test

100%

Prediction comparison

100%

Validation results file

100%

Step-by-step structure

100%

No subprocess sklearn call

100%

95%

Build Production ONNX Inference Service Component

ONNX Runtime inference optimization

Criteria

Without context

With context

Uses onnxruntime.InferenceSession

100%

Session options configuration

30%

50%

Input name lookup

100%

Model validation before inference

100%

Output verification

70%

100%

Error handling

100%

Numpy input arrays

100%

Reusable class or functions

100%

Step-by-step documentation

100%

No large model downloads

100%

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 87f14eb

Evaluated: about 1 month ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Deploy PyTorch Model to ONNX for Production Inference Standardize ML Model Deployment Across Platforms Build Production ONNX Inference Service Component

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.