tooluniverse-clinical-guidelines

Search and retrieve clinical practice guidelines from 12+ authoritative sources — NICE, WHO, NCCN, AHA, ADA, SIGN, USPSTF, IDSA, NIH consensus, ESMO/ESC/EASL European societies, and US specialty associations. Use for evidence-graded treatment recommendations, dosing protocols, screening guidance, and authoritative-source-prioritized clinical guidance (NICE/WHO ranked above society guidelines).

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-clinical-guidelines/SKILL.md

Quality

Content

56%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 rich in concrete tool guidance and parameters, but it is overly long and bloats context with general clinical knowledge Claude already possesses, and it is a single monolithic file rather than using progressive disclosure. Moving the clinical-reasoning and MCQ frameworks into bundled reference files and trimming textbook explanations would meaningfully raise both conciseness and progressive_disclosure.

Suggestions

Move the Diagnostic Test Selection, Lab Interpretation, Surgical Decision Making, and Clinical MCQ Reasoning sections into separate reference files under ./references/ and link to them from SKILL.md to improve both conciseness and progressive_disclosure.

Remove textbook explanations Claude already knows (SnNOut/SpPIn mnemonics, Holliday-Segar formula, Brown-Sequard segment rule, TLICS dimension values) and keep only tool-specific gotchas and workflow.

Add an explicit verification checkpoint in the search workflow (e.g., 'confirm at least 3 sources returned relevant results before synthesizing') to strengthen workflow_clarity feedback loops.

Dimension	Reasoning	Score
Conciseness	The 303-line body spends large sections explaining clinical knowledge Claude already knows (SnNOut/SpPIn, TLICS dimensions, Brown-Sequard lesion-level rule, Holliday-Segar fluid formulas, ASCVD statin hierarchy) that pad the skill well beyond what tool usage requires.	2 / 5
Actionability	Tool tables list concrete tool names, required parameters, and field-name gotchas ('Field is name, NOT title', 'use q not query', 'r.get(\"data\", [])'), giving mostly executable guidance with only minor gaps in full code examples.	4 / 5
Workflow Clarity	The search strategy is sequenced (start narrow, broaden, query 3+ sources, retrieve full text) with fallback paths, but validation checkpoints before synthesis are implicit rather than explicit 'verify before proceeding' steps.	4 / 5
Progressive Disclosure	Content is well-sectioned with headers, but the skill is monolithic — no references/, scripts/, or assets/ bundle files exist, so the large MCQ-reasoning and clinical-framework sections are inlined in SKILL.md rather than split into one-level-deep reference files.	3 / 5
	Total	13 / 20 Passed

Description

82%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 strong, with explicit 'what' and 'when' trigger guidance, named authoritative sources, and a distinctive niche. Its only mild weakness is that the action list is dominated by two verbs rather than a richer set of concrete operations.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ('Search and retrieve clinical practice guidelines') plus enumerates specific sources and use-cases (treatment recommendations, dosing protocols, screening guidance), but the core actions are limited to two verbs rather than a comprehensive action list.	3 / 5
Completeness	It explicitly answers 'what' (search and retrieve guidelines from named sources) and 'when' with a concrete trigger clause ('Use for evidence-graded treatment recommendations, dosing protocols, screening guidance...').	5 / 5
Trigger Term Quality	Strong natural-phrase coverage ('clinical practice guidelines', 'treatment recommendations', 'dosing protocols', 'screening guidance') plus authoritative-source names a clinician would say, though it omits synonyms like 'pathways' or 'care protocols'.	4 / 5
Distinctiveness Conflict Risk	A clear niche — clinical-practice-guideline retrieval from named authoritative bodies with an explicit source hierarchy — that is unlikely to trigger for the wrong skill and minimal conflict risk.	5 / 5
	Total	17 / 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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-clinical-guidelines/SKILL.md
Commit: 1b02920

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.