CtrlK
BlogDocsLog inGet started
Tessl Logo

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).

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced for tool use, but it is bloated with general clinical teaching Claude already knows and ships as a single large file with no progressive disclosure into references. Splitting the clinical-reasoning and tool-reference material into separate files would lift both weak dimensions.

Suggestions

Move general clinical knowledge (sensitivity/specificity, SnNOut/SpPIn, surgical timing, pediatric fluid formulas, TLICS/Brown-Sequard detail) into a reference file or remove it, keeping SKILL.md focused on tool-specific guidance Claude does not already know.

Extract the Tool Workflow tables, CPIC workflow, and Evidence Grading reference into a references/ file (e.g. TOOL_REFERENCE.md) and link to it from SKILL.md so the body stays a lean overview.

Tighten the Known Limitations and Fallback Strategy sections into a single compact troubleshooting block to reduce token overhead.

DimensionReasoningScore

Conciseness

The tool-workflow sections are lean and tool-specific, but large stretches (diagnostic test selection, SnNOut/SpPIn, surgical timing, TLICS/Brown-Sequard details, Holliday-Segar and Mosteller pediatric formulas) teach clinical concepts Claude already knows, so it is mostly efficient with unnecessary explanation that could be trimmed.

2 / 3

Actionability

Provides concrete tool names, required parameters, return-structure accessors (e.g. "result[0]['title']", "r.get('data', [])"), field-name gotchas ('cancer_type' NOT 'title', 'clinicalfunctionalstatus'), and a copy-ready synthesis template.

3 / 3

Workflow Clarity

The search strategy is a numbered sequence with parallel-call guidance, a 3-source minimum check, an explicit fallback strategy (NICE empty -> TRIP/GIN), and verification checklists for the MCQ workflow, matching the clear-sequence-with-checkpoints anchor.

3 / 3

Progressive Disclosure

No bundle files exist and the ~300-line body is a monolithic inline document; well-sectioned, but substantial reference material (tool tables, clinical reasoning frameworks) that should be split into separate files is kept inline, fitting the 'content that should be separate is inline' anchor rather than the under-50-line exception.

2 / 3

Total

10

/

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 specific, third-person, and explicitly provides both capabilities and use-case triggers, hitting all four anchors at the top level. It is concise despite listing many sources and avoids fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('Search and retrieve clinical practice guidelines', 'evidence-graded treatment recommendations, dosing protocols, screening guidance') and enumerates specific sources (NICE, WHO, NCCN, AHA, ADA, etc.), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' (search and retrieve guidelines from named sources) and 'when' via a 'Use for...' clause listing evidence-graded recommendations, dosing, and screening guidance.

3 / 3

Trigger Term Quality

Includes natural clinician-facing terms users would say ('clinical practice guidelines', 'treatment recommendations', 'dosing protocols', 'screening guidance') with good coverage; not merely technical jargon.

3 / 3

Distinctiveness Conflict Risk

Carves a clear clinical-guidelines niche with distinct source-prioritization triggers (NICE/WHO above society guidelines), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.