Scikit Survival

This is your go-to for survival analysis when you're dealing with censored time-to-event data. It wraps scikit-survival with clear guidance on choosing between Cox models, Random Survival Forests, Gradient Boosting, and SVMs depending on your data size and whether you need interpretability. The references cover the practical stuff like when to use Uno's C-index over Harrell's (anything above 40% censoring), how to handle competing risks, and why you should standardize features for regularized models. The model selection decision tree alone saves you from trial and error. If you're doing clinical research, reliability engineering, or churn prediction where not everyone experiences the event during observation, this handles the statistical complexity properly.

skills.sh installs: 329
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill scikit-survival --agent claude-code

Installs into .claude/skills of the current project.

Files

scikit-survival: Survival Analysis in Python

Overview

scikit-survival is a Python library for survival analysis built on top of scikit-learn. It provides specialized tools for time-to-event analysis, handling the unique challenge of censored data where some observations are only partially known.

Survival analysis aims to establish connections between covariates and the time of an event, accounting for censored records (particularly right-censored data from studies where participants don't experience events during observation periods).