confusion-matrix-generator

Confusion Matrix Generator - Auto-activating skill for ML Training. Triggers on: confusion matrix generator, confusion matrix generator Part of the ML Training skill category.

0.96x

Quality

Does it follow best practices?

Impact

72%

0.96x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/confusion-matrix-generator/SKILL.md

Evaluation results

69%

-11%

Flower Species Classifier Evaluation

Multi-class confusion matrix with sklearn

Criteria

Without context

With context

Approved library usage

100%

No arbitrary shell commands

100%

Production-ready structure

100%

Output validation

40%

Step-by-step phases

100%

Derived metrics computed

100%

Matrix normalization

Output file written

100%

Class labels preserved

100%

80%

Clinical Diagnostic Model Performance Assessment

Binary classification evaluation with derived metrics

Criteria

Without context

With context

Approved library for confusion matrix

No arbitrary shell commands

100%

Production-ready code structure

100%

TP/TN/FP/FN extracted

100%

Sensitivity and specificity computed

100%

Output validation

50%

Results saved to file

100%

Precision and F1 computed

100%

Step separation

100%

67%

-4%

Customer Support Ticket Classifier Evaluation Utility

Reusable confusion matrix pipeline module

Criteria

Without context

With context

Approved library for computation

No arbitrary shell commands

100%

Module/class structure

100%

Input validation in code

60%

20%

Normalized matrix output

Per-class metrics

100%

Step-by-step pipeline

100%

Output saved to file

100%

Demonstrates usage with provided data

100%

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3e83543

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Flower Species Classifier Evaluation Clinical Diagnostic Model Performance Assessment Customer Support Ticket Classifier Evaluation Utility

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.