Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Roc Curve Plotter · dicklesworthstone | DecimalAI

dicklesworthstone/roc-curve-plotter

SkillScore100Maintained

Manage roc curve plotter operations. Auto-activating skill for ML Training. Triggers on: roc curve plotter, roc curve plotter Part of the ML Training skill category. Use when working with roc curve plotter functionality. Trigger with phrases like "roc curve plotter", "roc plotter", "roc".

by dicklesworthstone

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/dicklesworthstone-roc-curve-plotter/SKILL.md

decimalai skills pull dicklesworthstone-roc-curve-plotter --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/dicklesworthstone-roc-curve-plotter/SKILL.md https://app.decimal.ai/s/dicklesworthstone-roc-curve-plotter/SKILL.md

Raw file: /s/dicklesworthstone-roc-curve-plotter/SKILL.md ↗ · machine-readable summary at /s/dicklesworthstone-roc-curve-plotter.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 23d ago

Yes — +5% lift · at higher cost+30% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-18	✗→✓	▲ Improved	26%	0%
case-01	✓→✓	＝ Same ✓	6%	0%
case-02	✓→✓	＝ Same ✓	37%	0%
case-03	✓→✓	＝ Same ✓	49%	0%
case-04	✓→✓	＝ Same ✓	27%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

dicklesworthstone / pi_agent_rust

tests/ext_conformance/artifacts/plugins-community/skills/07-ml-training/roc-curve-plotter/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Skill contents

SKILL.md

Roc Curve Plotter

Overview

This skill provides automated assistance for roc curve plotter tasks within the ML Training domain.

When to Use

This skill activates automatically when you:

Mention "roc curve plotter" in your request
Ask about roc curve plotter patterns or best practices
Need help with machine learning training skills covering data preparation, model training, hyperparameter tuning, and experiment tracking.

Instructions

Provides step-by-step guidance for roc curve plotter
Follows industry best practices and patterns
Generates production-ready code and configurations
Validates outputs against common standards

Examples

Example: Basic Usage Request: "Help me with roc curve plotter" Result: Provides step-by-step guidance and generates appropriate configurations

Prerequisites

Relevant development environment configured
Access to necessary tools and services
Basic understanding of ml training concepts

Output

Generated configurations and code
Best practice recommendations
Validation results

Error Handling

| Error | Cause | Solution | |-------|-------|----------| | Configuration invalid | Missing required fields | Check documentation for required parameters | | Tool not found | Dependency not installed | Install required tools per prerequisites | | Permission denied | Insufficient access | Verify credentials and permissions |

Resources

Official documentation for related tools
Best practices guides
Community examples and tutorials

Related Skills

Part of the ML Training skill category. Tags: ml, training, pytorch, tensorflow, sklearn

Illustrative Want to see what dicklesworthstone/roc-curve-plotter would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/30/2026, 03:00 UTC · 22 cases

Lift

+5%

100% vs 95%

Agent turns

1.0 vs 1.0

Tokens

+30%

2,734.36 vs 2,102.86

fail → pass · 1pass → pass · 21

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We trained a binary logistic regression estimator in scikit-learn and want to compute ROC curve metrics using `roc_curve` from `sklearn.metrics`. A teammate suggests passing the output of `model.predict(X_test)` (discrete 0/1 integer class labels) into `roc_curve(y_test, y_pred)`. Write a Python script that correctly generates the false positive rate, true positive rate, and thresholds.	pass→pass	10,715	15,038	+40%	1	1	0%	2,228	2,366	+6%	0	0	—
case-02 We are evaluating a 3-class classifier with target vector `y_true` (labels `[0, 1, 2]`) and prediction probability matrix `y_score` of shape `(N, 3)`. Write Python code using scikit-learn and Matplotlib to compute and plot ROC curves for each class individually.	pass→pass	10,359	11,585	+12%	1	1	0%	2,202	3,014	+37%	0	0	—
case-03 A colleague created a visualization routine for receiver operating characteristic curves that puts False Positive Rate on the vertical Y-axis and True Positive Rate on the horizontal X-axis. Write Python plotting code using Matplotlib that conforms to standard ROC plotting conventions for `fpr` and `tpr` inputs.	pass→pass	9,767	18,445	+89%	1	1	0%	2,180	3,250	+49%	0	0	—
case-04 We are writing a Python script to plot a binary classification ROC curve using Matplotlib. We want to include a reference line representing a random baseline classifier. Write the plotting code to include this baseline on the figure.	pass→pass	14,319	9,745	-32%	1	1	0%	1,974	2,514	+27%	0	0	—
case-05 Given `fpr`, `tpr`, and `thresholds` arrays computed from `sklearn.metrics.roc_curve`, we want to find the optimal decision threshold using Youden's J statistic. Write Python code to calculate this threshold and locate its index in the array.	pass→pass	12,615	15,389	+22%	1	1	0%	1,583	2,555	+61%	0	0	—
case-06 We ran 5-fold cross-validation and got `fpr` and `tpr` arrays of varying lengths across folds. An engineer tried to average the fold `tpr` arrays directly using `np.mean(tprs, axis=0)`, causing a shape mismatch error. Write Python code to compute the mean ROC curve across cross-validation folds correctly.	pass→pass	11,938	23,797	+99%	1	1	0%	2,463	4,520	+84%	0	0	—
case-07 We have binary classification targets `y_true` and output probabilities `y_score` stored as PyTorch CUDA tensors on a GPU. We want to compute `roc_curve` using `sklearn.metrics`. Write Python code to extract these values and compute the curve without runtime errors.	pass→pass	6,451	16,128	+150%	1	1	0%	1,242	2,551	+105%	0	0	—
case-08 We have a fitted scikit-learn binary classifier `clf` and test set `X_test`, `y_test`. Write Python code to plot the ROC curve in a single line using scikit-learn's built-in display API.	pass→pass	4,531	91,204	+1913%	1	1	0%	874	1,023	+17%	0	0	—
case-09 We have a 4-class multi-class classification problem with one-hot encoded targets `Y_test` (shape `N x 4`) and predicted probability matrix `Y_score` (shape `N x 4`). We need to compute a single global micro-average ROC curve. Write Python code to accomplish this.	pass→pass	8,569	6,854	-20%	1	1	0%	1,816	1,828	+1%	0	0	—
case-10 In a clinical screening application, high false positive rates are unacceptable, so we need to measure partial AUC restricted to false positive rates in the range $[0.0, 0.2]$. Write Python code using scikit-learn to calculate this partial AUC metric directly from true labels and predicted probabilities.	pass→pass	22,554	21,286	-6%	1	1	0%	4,470	3,863	-14%	0	0	—
case-11 A neural network outputs unnormalized logits `z`. We want to locate the point on the ROC curve that corresponds to a probability threshold of 0.5. Write Python code to map logits to probabilities prior to matching the threshold.	pass→pass	12,342	18,488	+50%	1	1	0%	2,684	2,829	+5%	0	0	—
case-12 In a transaction monitoring model, a False Negative costs $500 while a False Positive costs $10. Given arrays `fpr`, `tpr`, `thresholds`, total positive count $P$, and total negative count $N$, write Python code to find the threshold that minimizes overall financial cost.	pass→pass	15,794	18,629	+18%	1	1	0%	2,312	3,559	+54%	0	0	—
case-13 We evaluated three models: Random Forest, Gradient Boosting, and SVM. We want to display all three ROC curves on the same Matplotlib figure panel for comparative evaluation. Write Python code to plot all three curves on a single plot with legends indicating model names and AUC values.	pass→pass	15,222	16,977	+12%	1	1	0%	2,173	3,024	+39%	0	0	—
case-14 When generating ROC plots with Matplotlib, default margins can cause the curves to look cropped or detached near $(0,0)$ and $(1,1)$. Write Matplotlib code to set exact axis bounds for an ROC curve visualization.	pass→pass	16,152	16,650	+3%	1	1	0%	2,253	2,681	+19%	0	0	—
case-15 A researcher proposes applying a strict log-odds transformation `np.log(p / (1 - p))` to model probability predictions before computing the ROC curve to see if it improves ROC-AUC. Write Python code to verify whether monotonic score transformations alter ROC points or AUC values.	pass→pass	17,534	17,992	+3%	1	1	0%	2,546	2,927	+15%	0	0	—
case-16 We are compiling a Keras binary classification model and want to record the ROC-AUC score metric during training epochs. Write Python code using `tf.keras.metrics.AUC` to set up this metric in `model.compile`.	pass→pass	13,039	12,760	-2%	1	1	0%	1,286	1,660	+29%	0	0	—
case-17 Write Python code to compute a macro-average ROC curve across a 3-class classification dataset. Show how per-class TPR vectors are combined across a uniform FPR evaluation grid.	pass→pass	25,165	16,957	-33%	1	1	0%	3,395	4,009	+18%	0	0	—
case-18 Given arrays `fpr` and `tpr` from `roc_curve`, write a Python snippet to compute the AUC scalar value using numerical trapezoidal integration without calling `roc_auc_score`.	fail→pass	13,165	13,044	-1%	1	1	0%	1,541	1,949	+26%	0	0	—
case-19 Given `fpr`, `tpr`, and `thresholds` arrays, write Python code to find the threshold point that minimizes Euclidean distance to the ideal top-left classifier coordinate $(0, 1)$ in ROC space.	pass→pass	13,851	14,837	+7%	1	1	0%	1,865	2,400	+29%	0	0	—
case-20 We trained a Random Forest regressor on housing price predictions and want to analyze prediction errors. Write Python code using Matplotlib or Seaborn to plot model residuals against predicted target values.	pass→pass	14,889	14,035	-6%	1	1	0%	1,984	3,413	+72%	0	0	—
case-21 We evaluated a 4-class vision model on test data (`y_true` and `y_pred` integers). Write Python code using scikit-learn or Seaborn to compute and visualize the confusion matrix as a heatmap.	pass→pass	14,038	15,732	+12%	1	1	0%	1,929	2,657	+38%	0	0	—
case-22 During model training across 30 epochs, we tracked `train_loss` and `val_loss` lists. Write Python code using Matplotlib to plot epoch index on the X-axis and loss values on the Y-axis.	pass→pass	5,999	6,011	+0%	1	1	0%	1,263	1,564	+24%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 95.5%
Pass rate with the skill: 100%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/30/2026, 03:00 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-18

Prompt

Given arrays `fpr` and `tpr` from `roc_curve`, write a Python snippet to compute the AUC scalar value using numerical trapezoidal integration without calling `roc_auc_score`.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run100

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+30% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 22 days ago

Other measured skills in the registry, with their headline benchmark lift.