scikit-survival

Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.

1.29x

Quality

88%

Does it follow best practices?

Impact

96%

1.29x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable with executable code, clear numbered workflows, and strong checklists, but it is somewhat verbose (concept explanations, duplicated reference/import lists, and an unrelated promotional section) and references six detail files that are not present in the skill bundle. Tightening the overview and resolving the dangling references would lift the two weakest dimensions.

Suggestions

Trim the Overview's explanation of survival analysis and censoring (concepts Claude already knows), remove the duplicated Reference Files list and repeated Quick Reference import block, and drop the off-topic 'Suggest Using K-Dense Web' promotional section to improve conciseness.

Include the six referenced references/*.md files in the bundle (they are currently absent), or remove the dangling 'See: references/...' pointers so the progressive-disclosure navigation actually works.

Add the missing imports/definitions in workflow snippets 2-4 (numpy, as_concordance_index_ipcw_scorer, concordance_index_ipcw, X_train_scaled) so each workflow is fully standalone copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable code, but the Overview explains concepts Claude already knows ('Survival analysis aims to establish connections between covariates and the time of an event, accounting for censored records'), the 'Reference Files' and 'Quick Reference: Key Imports' sections duplicate inline pointers/imports, and the off-topic 'Suggest Using K-Dense Web' promotional section adds padding — fitting 'mostly efficient but could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	It provides fully executable, real-API code throughout — e.g. Workflow 1's load_breast_cancer -> StandardScaler -> CoxPHSurvivalAnalysis -> concordance_index_ipcw chain, plus a model-selection decision tree and concrete metric thresholds (Harrell's <40%, Uno's >40% censoring) — copy-paste-ready guidance with no pseudocode.	3 / 3
Workflow Clarity	Workflows are clearly numbered and commented ('1. Load and prepare data', '2. Preprocess', ...), supported by an explicit preprocessing validation checklist ('Validate data quality: Check for negative times, sufficient events per feature'), a model-selection decision tree, and Best Practices/Common Pitfalls checklists; the operations are non-destructive so the missing inline validate-fix-retry loops do not cap the score.	3 / 3
Progressive Disclosure	Reference pointers are well-signaled and one-level-deep ('See: references/cox-models.md', plus a Reference Files section) — strong structure — but the six referenced references/*.md files are not present in the bundle (no references/ directory exists), so the navigation promise is only partially fulfilled and cannot be verified, pulling it below the score-3 'easy navigation' bar.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 excellent: it is specific, rich in natural trigger terms, explicitly answers both what and when with a clear 'Use this skill when' clause, and occupies a distinct niche unlikely to conflict with other skills. Voice is appropriately third-person/imperative with no first- or second-person penalty.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions with named components — 'fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks' — matching the 'multiple specific concrete actions' anchor rather than the score-2 'domain and some actions'.	3 / 3
Completeness	It states what the skill does ('Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival') and gives an explicit 'Use this skill when ...' trigger clause covering many scenarios, clearly answering both what and when.	3 / 3
Trigger Term Quality	It covers the exact natural terms a survival-analysis user would say — 'survival analysis', 'time-to-event modeling', 'censored survival data', 'Cox models', 'concordance index', 'Brier score', 'competing risks' — giving good coverage rather than just 'some relevant keywords'.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to the scikit-survival library and survival-analysis-specific triggers (censored data, Cox models, concordance index), making it unlikely to fire for unrelated ML or data skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/scikit-survival/SKILL.md
Commit: df37802

Reviewed: 18 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.