scikit-survival

A comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival; use it when you need to model censored time-to-event outcomes, fit Cox/RSF/GB models or Survival SVMs, evaluate with C-index/Brier score, or handle competing risks.

Quality

88%

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

82%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.

A well-structured, highly actionable skill body with a complete runnable example and real reference files at one level of depth. Minor gaps in conciseness (placeholder scaffolding) and reference signaling keep it just short of top marks.

Suggestions

Remove the empty placeholder param_grid block and its commentary, or replace it with a real tunable example, to tighten the main example.

Replace the generic blockquote reference list with context-sensitive pointers, e.g. under Model families add 'Cox details: references/cox-models.md', to improve navigation signaling.

Add a brief validation note in the workflow (e.g. check event counts and non-negative times before fitting) as an explicit checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with task-relevant code and minimal concept explanation, but includes trimmable padding such as the empty placeholder param_grid with 'remove if unsupported' commentary and inline asides like 'shown for workflow completeness'.	4 / 5
Actionability	Provides a complete, copy-paste-ready runnable example (load_breast_cancer, train_test_split, Pipeline, CoxPHSurvivalAnalysis, concordance_index_ipcw) plus concrete code snippets for Surv construction, Harrell/Uno C-index, time-dependent AUC, and competing risks covering the common cases.	5 / 5
Workflow Clarity	The example is a clearly numbered six-step sequence (load, split, build pipeline, tune, predict, evaluate) with data-validation advice, but it lacks explicit validation checkpoints or feedback loops; acceptable since modeling is non-destructive, so no cap applies.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview and the six topic guides are real one-level-deep reference files, but they are listed in a generic blockquote ('may exist under:') rather than contextually signaled next to the relevant content, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

95%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.

A strong, specific description that clearly conveys both capabilities and trigger conditions with comprehensive natural keywords. The only weakness is second-person voice ('use it when you need to'), which the rubric penalizes.

Suggestions

Rephrase in third person to avoid the voice penalty, e.g. 'A comprehensive toolkit for survival analysis... Use when modeling censored time-to-event outcomes, fitting Cox/RSF/GB models or Survival SVMs, evaluating with C-index/Brier score, or handling competing risks.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (model censored time-to-event outcomes, fit Cox/RSF/GB models and Survival SVMs, evaluate with C-index/Brier score, handle competing risks) for comprehensive coverage, but the second-person phrasing 'use it when you need to' triggers the voice penalty reducing the score by 1.	4 / 5
Completeness	Explicitly answers both 'what' (toolkit for survival analysis and time-to-event modeling in Python using scikit-survival) and 'when' (use it when you need to model censored outcomes, fit these models, evaluate with these metrics, or handle competing risks) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms a survival-analysis user would say — 'survival analysis', 'time-to-event modeling', 'Cox', 'C-index', 'Brier score', 'competing risks', 'censored' — including synonyms across model families (Cox/RSF/GB/SVM).	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (survival/time-to-event analysis with scikit-survival) with distinct, specialized triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/scikit-survival/SKILL.md
Commit: f5ef65b

Reviewed: ~7 hours 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.