roc-curve-plotter
Roc Curve Plotter - Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter Part of the ML Training skill category.
35
3%
Does it follow best practices?
Impact
94%
1.04xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/roc-curve-plotter/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 essentially a skill title repeated with minimal useful information. It lacks concrete action descriptions, meaningful trigger terms, and any explicit 'Use when...' guidance. It would be very difficult for Claude to confidently select this skill from a large pool based on this description alone.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Plots ROC (Receiver Operating Characteristic) curves from classifier predictions, calculates AUC scores, and compares model performance across thresholds.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to plot ROC curves, evaluate classifier performance, compute AUC, visualize true positive vs false positive rates, or compare binary classification models.'
Remove the duplicated trigger term and expand with natural variations users might say, such as 'ROC', 'AUC', 'receiver operating characteristic', 'classification performance plot', 'model evaluation curve'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the skill ('Roc Curve Plotter') and its category ('ML Training') but does not describe any concrete actions like 'plots ROC curves from classifier outputs', 'calculates AUC scores', or 'compares model performance'. It is essentially a title repeated, not a capability description. | 1 / 3 |
Completeness | The description fails to clearly answer 'what does this do' beyond the name, and there is no explicit 'when should Claude use it' clause. The 'Triggers on' line is just the skill name repeated, not meaningful trigger guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms listed are just 'roc curve plotter' repeated twice. It misses natural user phrases like 'ROC curve', 'AUC', 'receiver operating characteristic', 'plot model performance', 'classification threshold', 'true positive rate', 'false positive rate', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'ROC curve' does provide some domain specificity that distinguishes it from generic plotting or data skills. However, the lack of detail about what it actually does (e.g., does it just plot, or also compute AUC, compare models?) and the vague 'ML Training' category could cause overlap with other ML visualization 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 template with no actual instructional content. It repeatedly references 'roc curve plotter' without ever providing any concrete guidance, code, or workflow for plotting ROC curves. It fails on every dimension as it contains only boilerplate meta-descriptions rather than actionable skill content.
Suggestions
Add executable Python code examples showing how to plot ROC curves using sklearn (e.g., `sklearn.metrics.roc_curve`, `sklearn.metrics.auc`) with matplotlib, including a complete working snippet.
Define a clear workflow: compute predictions → calculate FPR/TPR with `roc_curve()` → compute AUC → plot with matplotlib → save/display, with validation steps for common issues like binary vs. multiclass handling.
Remove all boilerplate sections (When to Use, Example Triggers, Capabilities) that describe the skill meta-information rather than teaching the actual task.
Add concrete examples covering common scenarios: binary classification ROC, multi-class one-vs-rest ROC, and comparing multiple models on the same plot.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know, repeats 'roc curve plotter' excessively, and contains no actual technical content about plotting ROC curves. | 1 / 3 |
Actionability | There is zero concrete guidance—no code, no commands, no specific steps for actually plotting an ROC curve. Every section is vague and abstract, describing what the skill supposedly does rather than instructing how to do it. | 1 / 3 |
Workflow Clarity | No workflow is defined at all. There are no steps, no sequence, and no validation checkpoints. The 'step-by-step guidance' mentioned in Capabilities is never actually provided. | 1 / 3 |
Progressive Disclosure | The content is a flat, uninformative page with no references to detailed materials, no code examples to navigate to, and no meaningful structure beyond boilerplate headings that contain no real 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.