Skip to main content
skill CX Codex

scikit-learn · eyadsibai — Claude Code skill: what it does, how to install

scikit-learn — a skill for classical ML in Python: it picks the algorithm and wires the pipeline so test data stays out of the fitting.

no license 124 installs ★ 7 updated 2026-01-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add eyadsibai/ltk --skill scikit-learn -a claude-code
Open on GitHub

What scikit-learn does

When a request mentions sklearn, classification, clustering or tuning, the skill hands the agent a selection table. Logistic regression as a baseline, random forest for everyday work, gradient boosting when accuracy on tabular data is the goal, SVM for wide feature spaces. Clustering and dimensionality reduction get their own tables, down to the parameter that decides the result, like n_clusters for KMeans or eps for DBSCAN.

Pipelines take up the middle of the file. Pipeline keeps every transform inside the training fold, ColumnTransformer routes different transforms to different columns, and the suggested preprocessing order is impute, then scale, then encode. For evaluation there are KFold, StratifiedKFold, TimeSeriesSplit and LeaveOneOut, plus a metric table per task.

Some limits are stated plainly. HalvingGridSearchCV needs sklearn 0.24 or newer. With lopsided classes, accuracy hides more than it shows, so the skill pushes you toward F1 or ROC-AUC. Fitting a scaler before the split is the leak it warns about hardest.

What it helps with

  • pick an algorithm for a tabular classification task
  • keep preprocessing inside the training fold
  • tune hyperparameters without a full grid sweep
  • choose a metric when classes are imbalanced
  • read learning curves to spot overfitting

Example prompts for the agent

  • Build a pipeline for this CSV: ColumnTransformer for the categoricals, StandardScaler for the numeric columns.
  • Split the data, run StratifiedKFold, and report F1 per fold.
  • Tune RandomForestClassifier with RandomizedSearchCV and show me the best params.

How to install scikit-learn

1Skills CLI (Vercel)

npx skills add eyadsibai/ltk --skill scikit-learn -a claude-code

2Manually: put the files in place

~/.claude/skills/scikit-learn/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/scikit-learn/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about scikit-learn

How do I install the scikit-learn skill in Claude Code?

Run npx skills add eyadsibai/ltk --skill scikit-learn -a claude-code. The skill lands at ~/.claude/skills/scikit-learn/SKILL.md.

What does this skill do?

It gives the agent a reference for classical ML: which estimator fits the task, how to arrange preprocessing in a pipeline, and which metrics or cross-validation scheme to use.

Why fit the scaler on training data only?

Transforms should only see the training split, otherwise the test rows shape the preparation and your score comes out too high. The skill suggests keeping the scaler inside Pipeline or fitting it on train alone.

Similar skills

All skills for AI and ML →

scikit-learn by other authors comes first.

scikit-learn K-Dense-AI A skill for Python machine learning tasks: classification, regression, clustering, preprocessing, and building ML pipelines with scikit-learn 1.9.1. CX Codex +1 2,400installs scikit-learn tondevrel This skill guides Claude Code through scikit-learn workflows, from preparing tabular data to evaluating a model. Use it for classical machine learning tasks. CX Codex +1 122installs scikit-learn-best-practices Mindrally scikit-learn-best-practices — a skill that hands your agent scikit-learn conventions: pipelines, cross-validation, metrics, model persistence. Useful when you write ML code in Python. CX Codex +1 940installs scikit-learn-expert 0xfurai scikit-learn-expert — an Claude subagent for scikit-learn: preprocessing, feature selection, model comparison and hyperparameter tuning, with pipelines and cross-validation throughout. CX Codex ★ 1,029repo stars pytorch-scikit-learn-cursorrules-prompt-file PatrickJS The pytorch-scikit-learn-cursorrules-prompt-file Cursor rule guides Python machine-learning work on chemistry problems with scikit-learn and PyTorch. It covers molecular data, model training, and evaluation. CX Codex +1 ★ 41,178repo stars pandas-scikit-learn-guide-cursorrules-prompt-file PatrickJS pandas-scikit-learn-guide-cursorrules-prompt-file directs Cursor to write vectorized Python data analysis code, follow PEP 8 standards, and keep Jupyter notebooks reproducible. CX Codex +1 ★ 41,178repo stars scikit-survival K-Dense-AI Builds reproducible survival analysis pipelines on scikit-survival 0.28.0. Covers right-censored outcomes, competing risks, model selection, and censoring-aware metrics. CX Codex +1 2,200installs Anomaly Detection aj-geddes Anomaly Detection is a Claude Code skill that finds outliers, fraud, and system faults with statistical tests, isolation forests, and deep learning. It generates Python analysis pipelines. CX Codex +1 534installs

From the same set11

The whole set →
literature-review literature-review walks the agent through a research review: database search, screening, synthesis, citation formatting and a PRISMA diagram. CX Codex +1 343installs resume-generator The resume-generator skill maps a job description to a candidate’s experience and reshapes the resume for that role. Use it when applying to different positions or changing careers. CX Codex +1 233installs scientific-computing scientific-computing points the agent at the right Python library for astronomy, bioinformatics, symbolic math or statistics, and shows the API for each. CX Codex +1 197installs webapp-testing webapp-testing uses Python Playwright to test local web apps, inspect rendered pages, capture screenshots, and perform browser actions. CX Codex +1 178installs content-writing content-writing is a Claude Code skill that guides an article from outline and research through section-by-section drafting and review to a final draft. CX Codex +1 175installs agent-browser This skill gives an AI agent CLI control over a browser for form entry, page scraping, screenshots, and PDF output. Use it for browser automation tasks. CX Codex +1 166installs stripe-payments stripe-payments gives your coding agent a working map of Stripe: hosted Checkout, custom Payment Intents, subscriptions, webhook signature checks, refunds and test cards. Useful once payment code has to leave the sandbox. CX Codex +1 161installs vector-databases Compares vector databases and index algorithms for RAG and semantic retrieval. Helps pick an engine based on dataset scale and metadata filtering needs. CX Codex +1 128installs

Project sponsors

Companies that keep this analytics open