sklearn-pipeline-builder

Sklearn Pipeline Builder - Auto-activating skill for ML Training. Triggers on: sklearn pipeline builder, sklearn pipeline builder Part of the ML Training skill category.

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill sklearn-pipeline-builder

What are skills?

0.98x

Quality

Does it follow best practices?

Impact

95%

0.98x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/sklearn-pipeline-builder/SKILL.md

SKILL.md

Review

Evals

Evaluation results

100%

Hospital Readmission Risk Predictor

End-to-end sklearn pipeline with data preparation

Criteria

Without context

With context

Pipeline object used

100%

ColumnTransformer used

100%

Preprocessing inside Pipeline

100%

Numerical scaling

100%

Categorical encoding

100%

Missing value handling

100%

Model serialisation

100%

Metrics written to file

100%

Fit on training split only

100%

Script executes

100%

Without context: $0.2680 · 1m 21s · 18 turns · 18 in / 4,122 out tokens

With context: $0.5269 · 1m 58s · 30 turns · 319 in / 6,101 out tokens

92%

Delivery Time Prediction Model Optimisation

Hyperparameter tuning within sklearn pipeline

Criteria

Without context

With context

Search wraps Pipeline

100%

Double-underscore parameter notation

100%

Cross-validation specified

100%

Model hyperparameters in search

100%

Preprocessor hyperparameters in search

100%

Best params written to file

100%

Best score written to file

100%

Fit on training split

Pipeline contains preprocessing

100%

Best pipeline saved

100%

Python script produced

100%

Without context: $0.2832 · 1m 24s · 17 turns · 18 in / 4,565 out tokens

With context: $0.5160 · 2m 3s · 30 turns · 63 in / 6,034 out tokens

94%

-2%

Credit Default Risk Model Comparison

Experiment tracking across model configurations

Criteria

Without context

With context

At least 3 configurations compared

100%

sklearn Pipeline per run

100%

Preprocessing inside Pipeline

100%

Algorithm/model name logged

100%

Hyperparameters logged per run

100%

Metric(s) logged per run

100%

Best configuration identified

63%

45%

Results in structured file

100%

Consistent metric across runs

100%

Best model saved

100%

Python script produced

100%

Without context: $0.4713 · 2m 4s · 25 turns · 25 in / 6,975 out tokens

With context: $0.5857 · 2m 16s · 30 turns · 61 in / 7,769 out tokens

Evaluated: 6 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Hospital Readmission Risk Predictor Delivery Time Prediction Model Optimisation Credit Default Risk Model Comparison

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.