confusion-matrix-generator
Inspect classifier errors with confusion matrices after predictions already exist. Use for per-class error analysis, threshold tradeoffs, and label-confusion diagnosis; not for regression metrics or full model training ownership.
npx skills add majiayu000/claude-skill-registry --skill confusion-matrix-generator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Confusion Matrix Generator ## Purpose Use this skill when the user already has classification outputs and needs to understand where the model is getting confused. ## When to Use Use this skill when: - Breaking down false positives and false negatives by class - Comparing thresholds or class weights for a classification model - Explaining which classes are systematically confused with one another ## Not For / Boundaries - Regression evaluation: use `evaluating-machine-learning-models` - Leakage audits: use `ml-data-leakage-guard` - End-to-end training runs: use `training-machine-learning-models` ## Typical Outputs - Confusion matrix tables or heatmaps - Per-class precision/recall breakdowns - Actionable notes on thresholding, relabeling, or class balancing ## Related Skills - `evaluating-machine-learning-models` for the broader metric suite - `feature-importance-analyzer` when the next question is why a class fails
- Purpose
- When to Use
- Not For / Boundaries
- Typical Outputs
- Related Skills
What does the confusion-matrix-generator skill do?
Inspect classifier errors with confusion matrices after predictions already exist. Use for per-class error analysis, threshold tradeoffs, and label-confusion diagnosis; not for regression metrics or full model training ownership.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill confusion-matrix-generator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.