CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

87%

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

The canonical home for this skill is tooluniverse-clinical-trial-matching in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured and concrete, with dense tool/parameter tables, a clear 10-phase workflow, and explicit error-handling/verification guidance. The main gaps are missing inline code examples and the seven referenced bundle files that do not exist on disk.

Suggestions

progressive_disclosure: Add the seven referenced bundle files (TOOLS_REFERENCE.md, MATCHING_ALGORITHMS.md, SCORING_CRITERIA.md, REPORT_TEMPLATE.md, TRIAL_SEARCH_PATTERNS.md, EXAMPLES.md, QUICK_START.md) to ./references/ — currently every link is dead, so the carefully designed navigation leads nowhere.

actionability: Include at least one complete, copy-paste tool-call sequence inline (e.g., search_clinical_trials -> get_clinical_trial_descriptions -> eligibility/locations batch) so the common case is executable without opening EXAMPLES.md.

conciseness: Remove redundancy — fold 'Critical Parameter Notes' into the tool tables and collapse 'Parallelization Strategy' into the workflow phases it restates.

DimensionReasoningScore

Conciseness

Largely efficient and information-dense (tool tables, scoring breakdown, gene-ID map) with no padding about concepts Claude already knows, but minor redundancy remains — the 'Parallelization Strategy' restates the workflow phases and 'Critical Parameter Notes' duplicates the tool tables above. Not a 5 because not every token earns its place; not a 3 because the bulk is high-value rather than unnecessary explanation.

4 / 5

Actionability

Highly concrete guidance — exact tool names, required parameters, literal values like action="search_studies" and eligibility_criteria="all", plus a CIViC gene-ID table — but there is no complete copy-paste code example inline and the EXAMPLES/QUICK_START files that would supply them are absent. Not a 5 (no fully executable common-case example); not a 3 (guidance is specific and real, not pseudocode).

4 / 5

Workflow Clarity

A clearly sequenced 10-phase workflow with verification present via the Error Handling section (try/except, fallback tools) and a mandatory completeness checklist, so the batch-operation validation cap does not apply. Not a 5 because validation lives in a separate section rather than being woven through each phase; not a 3 because checkpoints are not merely implicit.

4 / 5

Progressive Disclosure

Good one-level-deep structure with a dedicated, well-signaled Reference Files table pointing to seven split-out .md files and conceptually appropriate content separation. Not a 5 because none of those seven referenced bundle files actually exist in ./references/, so navigation breaks; not a 3 because the structure and signaling themselves are clear.

4 / 5

Total

16

/

20

Passed

Description

100%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 excellent: third-person, concrete, and comprehensive, with an explicit 'Use for' trigger clause and named data sources that establish a distinct niche. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with named systems — 'Transforms a patient's molecular profile ... into ranked clinical-trial recommendations', 'Searches ClinicalTrials.gov, the EU CTIS register ... AND the ISRCTN registry', 'cross-references CIViC, OpenTargets, ChEMBL, and FDA labels' — giving comprehensive coverage rather than just naming the domain.

5 / 5

Completeness

Explicitly answers both 'what' (transforms molecular profile + clinical state into ranked, evidence-tiered recommendations across three registers and four reference DBs) and 'when' (a concrete 'Use for ...' clause with multiple trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use for' clause supplies natural phrases users would actually say — 'matching patients to trials by genotype', 'biomarker-driven trial selection', 'trial-eligibility scoring', 'finding trials across the US, Europe, and the UK' — with good synonym coverage (genotype/biomarker).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — precision-oncology / rare-disease patient-to-trial matching by molecular biomarker — with distinct triggers and minimal overlap with adjacent skills; voice is third person ('Transforms', 'Searches', 'Use for') with no first/second-person penalty.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 9 missing

Warning

Total

15

/

16

Passed

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.