clinical-decision-support

Prepare and validate research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation.

Quality

86%

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 well-structured, actionable skill body that defers detail to real one-level-deep reference files and gives executable commands throughout. Its main weakness is mild verbosity, particularly the citation section, and the lack of an explicit retry loop in the main workflow.

Suggestions

Tighten or relocate the "Citing Scientific Agent Skills" section into a reference file to recover tokens from the main body.

Add an explicit validate→fix→retry loop note in the Workflow (e.g., when a script reports missing fields, fix and re-run before human review) to lift workflow_clarity to 5.

Consider trimming the long bullet lists in sections like Aggregate Model and Biomarker Evaluation into the corresponding reference files, keeping only the decision-critical items inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no basic-concept padding), but the lengthy "Citing Scientific Agent Skills" section and several dense methodological lists add tokens that could be trimmed; not a 5 because of those minor over-explanation instances.	4 / 5
Actionability	Provides copy-paste-ready bash commands for every helper, a concrete need→asset→script table, named template starting points (e.g. assets/artifact_intended_use_template.json), and executable verification commands, fully covering the common cases.	5 / 5
Workflow Clarity	A clear four-step workflow with an explicit Data Gate precondition and a Verification section, plus script-level validation; falls short of 5 because the main workflow lacks an explicit validate→fix→retry feedback loop, though the destructive/batch cap does not apply since validation steps are present.	4 / 5
Progressive Disclosure	SKILL.md is an overview with a well-signaled, one-level-deep Reference Map and a need→asset/script table; all cited references/, scripts/, and assets/ files exist, content is appropriately split, and navigation is easy.	5 / 5
	Total	18 / 20 Passed

Description

87%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 precise, third-person description that clearly states both capability and usage triggers while sharply bounding the skill against clinical-care use. It is comprehensive and low-conflict, with only minor room for more action verbs and synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Prepare and validate") applied across a comprehensive list of artifact types (evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, governance); falls just short of the score-5 anchor, which expects multiple distinct concrete verbs rather than two verbs reused over a domain catalog.	4 / 5
Completeness	Explicitly states what ("Prepare and validate research-only ... artifacts") and when ("Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation"), matching the score-5 anchor that requires both what and an explicit trigger clause with concrete phrases.	5 / 5
Trigger Term Quality	Strong natural keywords a researcher would say ("clinical decision-support", "evidence-profile", "cohort", "survival", "biomarker/model", "aggregate or synthetic research documentation", "traceability") with explicit trigger phrasing; not quite a 5 because it omits common synonyms and file/extension variations.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (research-only CDS evaluation/governance artifacts) with distinct triggers and an explicit negative boundary ("not patient care or live clinical operation"), giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 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/clinical-decision-support/SKILL.md
Commit: 49c6e97

Reviewed: 11 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.