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

75%

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-trial-matching/SKILL.md

Quality

Content

50%

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 and rich in concrete tool/parameter reference, but it is padded with motivational prose, lacks executable code examples, defers key algorithms to files that are not present in the bundle, and omits explicit per-phase validation for its batch operations.

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) or remove the dead links — currently every progressive-disclosure reference 404s.

Trim the exhortation sections ('LOOK UP, DON'T GUESS', 'COMPUTE, DON'T DESCRIBE', KEY PRINCIPLES) to one line each and move the large tool/scoring tables into TOOLS_REFERENCE.md / SCORING_CRITERIA.md to slim the SKILL.md overview.

Add at least one executable example (a sample search_clinical_trials call with arguments filled in, or a Python scoring snippet) and insert explicit validation checkpoints between the batch phases (e.g., verify non-empty NCT list and eligibility parse before scoring).

Dimension	Reasoning	Score
Conciseness	Tool/parameter tables and scoring formulas are high-value reference content Claude lacks, but exhortation sections ('LOOK UP, DON'T GUESS', 'COMPUTE, DON'T DESCRIBE', the 10-item KEY PRINCIPLES list) pad the body with motivational prose. Mostly efficient but could be tightened; not a 3 because several tokens restate obvious guidance.	2 / 3
Actionability	Concrete tool names, required parameters, CIViC gene IDs, and numeric scoring tables are highly specific, but the body contains no executable code or filled-in example tool calls, and the actual matching/scoring algorithms are deferred to referenced files. Not a 3 because guidance is not copy-paste executable; not a 1 because parameter-level detail is genuinely concrete.	2 / 3
Workflow Clarity	A clear 10-phase sequence with a completeness checklist and an error-handling section, but batch operations (trial detail 'groups of 10') lack explicit per-phase validation checkpoints. Per the rubric, missing validation in batch workflows caps this at 2; not a 1 because the sequence and feedback guidance are present.	2 / 3
Progressive Disclosure	References are clearly signaled and one level deep (TOOLS_REFERENCE.md, MATCHING_ALGORITHMS.md, SCORING_CRITERIA.md, etc.), but none of these files exist in references/scripts/assets, so every link is dead, and large tool/scoring tables that belong in those files remain inline. Not a 3 because navigation leads to missing files; not a 1 because in-body structure is well organized.	2 / 3
	Total	8 / 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.

A strong, third-person description that names concrete actions, surfaces natural trigger terms, and gives an explicit 'Use for' clause covering both what and when. It is distinctive within its skill family with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Transforms a patient's molecular profile... into ranked clinical-trial recommendations', 'Searches ClinicalTrials.gov, the EU CTIS register... ISRCTN registry', and 'cross-references CIViC, OpenTargets, ChEMBL, and FDA labels'. Matches the score-3 anchor of multiple specific concrete actions; not below because nothing here is vague.	3 / 3
Completeness	Clearly answers both what ('transforms... into ranked clinical-trial recommendations with evidence tiers') and when via an explicit 'Use for...' clause. Matches the score-3 anchor; not a 2 because the when-trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	Natural user-facing terms appear explicitly: 'matching patients to trials by genotype, biomarker-driven trial selection, trial-eligibility scoring, and finding trials across the US, Europe, and the UK'. Good coverage of phrasings a user would actually say; not below because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (precision-oncology / rare-disease trial matching across specific registries) with distinct triggers unlikely to fire for other skills. Not below because the scope is sharply bounded against sibling tooluniverse skills.	3 / 3
	Total	12 / 12 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: 089eb8e

Reviewed: about 6 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.