Skip to main content
affpapa.org
RU EN
skill

scikit-learn · davila7 — Claude Code skill: ML in Python

A Claude skill that steers the agent through scikit-learn work: classification, clustering, preprocessing, pipelines and hyperparameter tuning.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill scientific/scikit-learn
Open on GitHub

What scikit-learn does

The skill hands the agent a reference set for scikit-learn. It covers supervised and unsupervised algorithms, evaluation metrics, cross-validation, missing-value handling, categorical encoding and pipeline assembly. The material lives in files such as references/supervised_learning.md, references/unsupervised_learning.md, references/model_evaluation.md and references/preprocessing.md. When you ask for a model or a data prep step, the agent pulls the matching section.

Install it with npx claude-code-templates@latest --skill scientific/scikit-learn or npx skills add davila7/claude-code-templates --skill scikit-learn -a claude-code. The skill itself ships no library code. scikit-learn still has to be present in your project, for instance via uv pip install scikit-learn; the examples also lean on matplotlib and seaborn for plots and on pandas and numpy for tables.

It earns its place when you compare several algorithms on one dataset or wire up a pipeline over mixed feature types. If you already keep your own snippet collection and would rather the agent not reach for outside examples, this one gets in the way.

What it helps with

  • build a pipeline over numeric and categorical features
  • tune hyperparameters with GridSearchCV or RandomizedSearchCV
  • score a model with precision, recall and ROC AUC
  • impute missing values and encode categories before training
  • cut dimensionality with PCA or t-SNE

Example prompts for the agent

  • Split the data into train and test with stratification, then fit a RandomForestClassifier
  • Build a Pipeline with ColumnTransformer: scale the numeric features and encode the categorical ones
  • Run cross-validation across several models and print the metrics for each

How to install scikit-learn

1claude-code-templates

npx claude-code-templates@latest --skill scientific/scikit-learn

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill scikit-learn -a claude-code

3Manually: 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 scikit-learn in Claude Code?

Run npx claude-code-templates@latest --skill scientific/scikit-learn, then npx skills add davila7/claude-code-templates --skill scikit-learn -a claude-code. The skill file lands at ~/.claude/skills/scikit-learn/SKILL.md.

What does the scikit-learn skill do?

It gives the agent reference material on scikit-learn algorithms, metrics, preprocessing and pipelines, so the code it writes follows the library instead of guesswork.

Do I still need to install scikit-learn itself?

Yes. The skill does not install the library. Add it to your project separately, for example with uv pip install scikit-learn.

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 2,200installs scikit-learn-best-practices Mindrally 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 888installs scikit-survival K-Dense-AI A skill that walks an agent through scikit-survival 0.28.0: building, tuning and auditing survival models on censored data, with metrics that account for censoring. CX Codex +1 2,000installs Anomaly Detection aj-geddes Detect outliers, fraud, and system faults using statistical tests, isolation forests, and deep learning. Generates working Python analysis pipelines. CX Codex +1 523installs data-scientist VoltAgent Community Subagent for exploratory data analysis, hypothesis testing, and building machine learning models directly in Claude Code. 3,342installs probabl-skills probabl-ai Machine learning experimentation skills for Python projects. Guides agents through pipeline design, evaluation routines, and Skore report tracking. ★ 143repo stars statistics-math pluginagentmarketplace A coding-agent skill with Python recipes for statistics, probability, linear algebra and regression. Useful when you need to compute metrics or test a hypothesis. CX Codex +1 432installs

From the same set495

The whole set →
pubmed-database A Claude skill for PubMed access over the E-utilities REST API: MeSH queries, batch fetches, citation matching by PMID or DOI. 149installs prompt-engineering-dspy Learn to structure language-model tasks with DSPy, assemble RAG workflows, and tune modules from examples. Useful when a project needs more than a hand-written prompt. 147installs typescript-pro Get help with advanced TypeScript types, generic constraints, and strict compiler settings. Use it when shaping shared contracts or diagnosing difficult type inference. 146installs timeline-compressor Compresses a real-world timeline into fast simulation cycles so you can test decisions and risks sooner. Useful before you commit to a plan. 146installs crewai Designs multi-agent teams on CrewAI: roles, tasks, orchestration and process types. Useful once a single agent stops being enough. 141installs perplexity This skill wires Perplexity into Claude: web search, conversational answers, and deep research through an agent. Handy when you need current information rather than library docs. 140installs api-fuzzing-bug-bounty This skill guides security checks for REST, SOAP, and GraphQL APIs. Use it to structure authorized bug bounty work or an API security assessment. 139installs dependency-updater A skill that detects your project type, applies safe dependency updates on its own and asks before touching major versions. 136installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor