relsa-severity-assessment

Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. Use when combining welfare readouts — body weight or weight loss, body temperature, clinical or nesting scores, biomarkers, activity, heart rate, burrowing, wheel running — into one severity score per animal per day, when asking which animals are at risk of reaching a humane endpoint or when one will be reached, when defining attention/danger zones or thresholds on a severity scale by kernel density estimation, or when reporting severity for a 3Rs, refinement, animal-welfare, or EU Directive 2010/63/EU severity-assessment context. Covers directionality ("turned" variables), baseline normalization, reference sets, RELSA weights, ARIMA prediction intervals, and RMSE/PICP/MPIW evaluation.

Quality

89%

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

86%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 thorough, executable skill body with a clear three-step workflow and well-structured one-level-deep references into real bundle files. It is slightly verbose in its prose rationale but every section carries domain-specific, non-obvious guidance.

Dimension	Reasoning	Score
Conciseness	Information-dense and avoids explaining concepts Claude already knows, but the prose rationale sections (Overview, four decisions) are somewhat expansive and could be tightened without losing load-bearing domain guidance.	4 / 5
Actionability	Fully executable copy-paste bash and Python snippets for each step, with realistic example outputs and runnable commands tied to assets/example_cohort.csv, covering the common cases end-to-end.	5 / 5
Workflow Clarity	A clear three-step sequence (compute scores → forecast → zones) with built-in verification cues (echoed reference model, bandwidth sweep, warning-driven checks), though explicit validate-fix-retry loops are only implicit.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to real bundle files (scripts/.py, references/.md, assets/example_cohort.csv), with detail appropriately split out and easy navigation via the Resources section.	5 / 5
	Total	18 / 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.

A well-crafted description that concretely states capabilities and provides an explicit, multi-scenario 'Use when' trigger clause in third-person voice. It is comprehensive and highly distinct within its specialized domain.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — combining welfare readouts into one per-animal severity score, predicting humane-endpoint timing via ARIMA, defining attention/danger zones by KDE, and reporting for 3Rs/EU Directive contexts — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Multivariate severity assessment and humane endpoint prediction... using the RELSA score and ARIMA-based foRcast forecasting') and when via a concrete 'Use when...' clause enumerating four trigger scenarios.	5 / 5
Trigger Term Quality	Strong natural-term coverage with synonyms ('body weight or weight loss', 'clinical or nesting scores') and domain triggers ('humane endpoint', '3Rs', 'refinement', 'EU Directive 2010/63/EU'), though the density is jargon-heavy and a few common lay phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (RELSA severity assessment for lab animal studies) with distinctive triggers (humane endpoint, 3Rs/refinement, EU Directive 2010/63/EU) and minimal overlap risk with adjacent forecasting or stats skills.	5 / 5
	Total	19 / 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/relsa-severity-assessment/SKILL.md
Commit: 49c6e97

Reviewed: 2 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.