Back to resources

SKILL

scikit-survival

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/scikit-survival
Use with an agent

SUMMARY

What it does

This Agent Skill provides procedural guidance for building, evaluating, and auditing right-censored or competing-risk survival workflows using scikit-survival. It covers leakage-safe preprocessing, model selection, probability prediction, and censoring-aware metrics. The skill includes executable examples, reference files, and bundled local CLIs for validation, training, evaluation, and reporting. It emphasizes non-negotiable workflow steps to avoid data leakage and ensure correct metric usage. The skill is MIT-licensed, but the upstream scikit-survival package is GPL-3.0-or-later. It requires Python 3.11+, uv, and a pinned dependency stack. The skill does not provide clinical advice or causal evidence.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

data.analysisweight 90 · confidence 90software.developmentweight 70 · confidence 80research.supportweight 80 · confidence 85

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.