scikit-survival

Build, evaluate, and audit right-censored or competing-risk survival workflows with scikit-survival, including leakage-safe preprocessing, model selection, probability prediction, and censoring-aware metrics.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an efficient, actionable overview with executable code, an explicit validation-rich workflow, and clean one-level-deep progressive disclosure to verified reference files. Minor trimming of pinned-version detail would push conciseness to 5.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence — no padding about what survival analysis is — but the dated runtime bounds, pinned versions, and a few explanatory sentences could be trimmed further without losing clarity.	4 / 5
Actionability	Copy-paste-ready executable code blocks for outcome construction, leakage-safe pipelines, prediction/metrics, and bundled CLI flows, with concrete commands covering the common cases.	5 / 5
Workflow Clarity	The 'Non-negotiable workflow' is a numbered 10-step checklist with explicit validation/sequencing checkpoints (split before preprocessing, fit censoring on training, restrict eval times, match predictions to metrics), and the CLI flow chains validate→train→evaluate→report with clear ordering.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with six well-signaled one-level-deep references (all verified to exist in ./references/) plus a dedicated 'Reference files' index; no nested references and easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, technically rich, and highly distinctive, but it omits an explicit 'when to use' trigger clause, capping completeness at 3 despite strong 'what' coverage. Adding a 'Use when...' sentence would raise the completeness dimension.

Suggestions

Append an explicit trigger clause, e.g. 'Use when working with right-censored or competing-risk time-to-event data in scikit-survival.'

Include a common natural-language synonym like 'time-to-event' or 'Kaplan-Meier/Cox' so users who don't say 'survival' still match.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'build, evaluate, and audit', 'leakage-safe preprocessing, model selection, probability prediction, and censoring-aware metrics' — with comprehensive coverage of the survival-analysis workflow.	5 / 5
Completeness	The 'what' is concrete and detailed, but there is no explicit 'Use when...' clause telling Claude when to invoke the skill, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Strong domain keywords ('survival workflows', 'right-censored', 'competing-risk', 'censoring-aware metrics') but the natural user phrasing leans technical; a few common synonyms (e.g. 'time-to-event', 'Kaplan-Meier', 'Cox') are absent.	4 / 5
Distinctiveness Conflict Risk	A narrow, clearly defined niche (scikit-survival right-censored/competing-risk modeling) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/scikit-survival/SKILL.md
Commit: b2a92ba

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.