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.

Quality

81%

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

71%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 well-structured with strong progressive disclosure and largely executable code, but it leans verbose — restating known concepts and duplicating guidance across 'When to Use', 'Best Practices', and 'Common Pitfalls' — and a couple of workflows omit imports. Tightening prose and making example imports self-contained would raise the score.

Suggestions

Remove or trim conceptual restatements Claude already knows (e.g. the 'Survival analysis aims to establish connections...' paragraph) and consolidate overlapping guidance between 'When to Use This Skill', 'Best Practices', and 'Common Pitfalls'.

Make every code block self-contained: add the missing `import numpy as np` in Workflow 2 and the `from sksurv.metrics import as_concordance_index_ipcw_scorer` import in Workflows 3 and the scikit-learn integration section.

Add explicit validation checkpoints to the workflows (e.g. verify sufficient events per feature, check Cox proportional-hazards assumptions, confirm model convergence) so errors are caught before evaluation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with abundant executable code, but several sections restate concepts Claude already knows ('Survival analysis aims to establish connections between covariates and the time of an event...') and 'When to Use', 'Best Practices', and 'Common Pitfalls' overlap considerably.	3 / 5
Actionability	Copy-paste-ready code with concrete imports and parameters across most workflows; minor gaps — Workflow 2 uses np without importing numpy and Workflow 3 references as_concordance_index_ipcw_scorer without importing it.	4 / 5
Workflow Clarity	Four numbered workflows show a clear load → preprocess → fit → predict → evaluate sequence, but validation checkpoints (e.g. confirming model convergence or checking data assumptions before fitting) are implicit rather than explicit.	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled one-level-deep references to six real reference files (verified present in references/), each linked inline at the relevant section and summarized in a Reference Files block.	5 / 5
	Total	16 / 20 Passed

Description

92%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, complete, and well-targeted: it names concrete model families and metrics, gives explicit 'Use when...' trigger guidance, and occupies a distinct niche. Minor gaps in synonym coverage keep trigger term quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks' — giving comprehensive coverage of the toolkit's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival') and 'when' ('Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models...').	5 / 5
Trigger Term Quality	Strong natural terms — 'survival analysis', 'time-to-event modeling', 'censored survival data', 'Cox models', 'competing risks' — with synonyms, though a few common user phrasings (e.g. 'Kaplan-Meier') are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche tied to the scikit-survival library and survival analysis; triggers are distinct and unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/scikit-survival/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.