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

92%

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

85%

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, actionable, and uses progressive disclosure effectively with verified one-level-deep references and clear validation checkpoints. Its main weakness is moderate verbosity from recurring safety caveats and time-sensitive regulatory detail embedded inline rather than isolated.

Suggestions

Move dated regulatory specifics (e.g., "FDA's January 2026 CDS guidance") into references/regulatory_and_governance.md and keep the body pointer-only, so time-sensitive detail does not clutter the overview.

Consolidate the recurring research-only / not-patient-care caveats into the Hard Safety Boundary and Data Gate sections, referencing them rather than restating throughout.

Dimension	Reasoning	Score
Conciseness	Most sections are lean do/don't lists, but the inline dated regulatory detail ("FDA's January 2026 CDS guidance") is time-sensitive information placed in the main flow rather than a deprecated/old-patterns section, and safety caveats recur across several sections, so it could be tightened.	2 / 3
Actionability	Provides a concrete need→asset→script selection table, copy-paste executable commands ("python3 scripts/validate_cds_artifact.py --help"), and explicit verification commands (unittest discover, AST compilation), all directly runnable.	3 / 3
Workflow Clarity	The numbered workflow (Frame question → Select artifact → Run locally → Human review) is clearly sequenced, with a pre-script Data Gate checklist as an explicit validation checkpoint and stated feedback on what script success does and does not mean.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with per-section "See references/X.md" signals and a consolidated Reference Map; all 26 referenced reference/asset/script files were verified to exist, and references are one level deep with easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concise, concrete, and third-person with an explicit "Use for..." trigger and a sharp negative boundary. It cleanly answers both what the skill does and when to use it. No notable weaknesses.

Dimension	Reasoning	Score
Specificity	Enumerates concrete artifact capabilities—"evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts"—mapped to the actions "Prepare and validate", giving multiple specific concrete outputs rather than vague language.	3 / 3
Completeness	Clearly states what it does ("Prepare and validate research-only clinical decision-support evaluation...") and when to use it via an explicit "Use for aggregate or synthetic research documentation and traceability—not patient care or live clinical operation" trigger clause.	3 / 3
Trigger Term Quality	Uses natural domain terms a clinical researcher would say—"clinical decision-support", "cohort", "survival", "evidence-profile", "biomarker/model", "aggregate"—with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The narrow research-only framing plus the explicit negative boundary ("not patient care or live clinical operation") carves a clear niche unlikely to conflict with general documentation or clinical-care skills.	3 / 3
	Total	12 / 12 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: 757b63b

Reviewed: about 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.