tooluniverse-clinical-trial-matching

AI-driven patient-to-trial matching for precision oncology and rare-disease care. Transforms a patient's molecular profile (mutations, biomarkers, expression) and clinical state into ranked clinical-trial recommendations with evidence tiers. Searches ClinicalTrials.gov, the EU CTIS register (European/EEA trials), AND the ISRCTN registry (UK/international) plus cross-references CIViC, OpenTargets, ChEMBL, and FDA labels. Use for matching patients to trials by genotype, biomarker-driven trial selection, trial-eligibility scoring, and finding trials across the US, Europe, and the UK.

Quality

81%

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

Quality

Content

71%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 content is well-structured and actionable at the tool-parameter level, with a clear phased workflow and error-handling guidance. Its main weakness is progressive disclosure: the body depends on seven referenced files that do not exist in the bundle, so the promised navigation leads nowhere and the executable code is effectively inaccessible.

Suggestions

Ship the referenced bundle files (TOOLS_REFERENCE.md, MATCHING_ALGORITHMS.md, SCORING_CRITERIA.md, REPORT_TEMPLATE.md, TRIAL_SEARCH_PATTERNS.md, EXAMPLES.md, QUICK_START.md) under ./references/ so the in-body links resolve and the executable code they hold is actually available.

Add explicit inter-phase validation checkpoints to the Workflow Overview (e.g., 'Before Phase 2, confirm disease resolved to an EFO/ontology ID; if not, retry OLS/OpenTargets') to turn the implied validation into a feedback loop for this batch operation.

Tighten redundancy between the Workflow Overview, 'Critical Tool Parameters', and 'Parallelization Strategy' sections so the body is leaner and each token earns its place.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely assumes Claude's competence (no concept filler, exact tool parameters, a CIViC gene-ID table), but at ~250 lines it has some redundancy — the 'Critical Tool Parameters' tables and 'Parallelization Strategy' partially restate the Workflow Overview phases.	4 / 5
Actionability	Concrete tool names with exact required parameters and a batch-tool parameter table give mostly executable guidance, but the body contains no copy-paste code — the actual executable code is referenced out to MATCHING_ALGORITHMS.md / TRIAL_SEARCH_PATTERNS.md, which are missing.	4 / 5
Workflow Clarity	A clearly sequenced 10-phase Workflow Overview plus an Error Handling section with try/except, fallback tools, and a completeness checklist provide validation guidance for this batch skill, but explicit inter-phase validation checkpoints are only implied rather than stated.	4 / 5
Progressive Disclosure	Structure is well-organized with a Reference Files table signaling seven one-level-deep files, but every referenced bundle file (TOOLS_REFERENCE.md, MATCHING_ALGORITHMS.md, SCORING_CRITERIA.md, REPORT_TEMPLATE.md, TRIAL_SEARCH_PATTERNS.md, EXAMPLES.md, QUICK_START.md) is absent — the references resolve to nothing, breaking navigation.	3 / 5
	Total	15 / 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.

The description is strong: it concretely states what the skill does, names the specific registries and databases it uses, and provides an explicit 'Use for' clause with concrete trigger tasks. The only minor weakness is that trigger phrasings lean toward task descriptions rather than verbatim user questions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Transforms a patient's molecular profile...into ranked clinical-trial recommendations with evidence tiers', 'Searches ClinicalTrials.gov, the EU CTIS register...ISRCTN registry', and cross-references 'CIViC, OpenTargets, ChEMBL, and FDA labels' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Transforms a patient's molecular profile...into ranked clinical-trial recommendations with evidence tiers') and 'when' (a clear 'Use for...' clause with concrete trigger phrases), matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	The 'Use for matching patients to trials by genotype, biomarker-driven trial selection, trial-eligibility scoring, and finding trials across the US, Europe, and the UK' clause covers relevant task phrasings, but these are task-type descriptors rather than the verbatim natural questions users say, and some synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The 'AI-driven patient-to-trial matching for precision oncology and rare-disease care' niche with named registries and databases is a tight, distinct domain with minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 9 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-clinical-trial-matching/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.