Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mims-harvard/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.
Passed 9 of 14 test cases with the skill, and 6 of 14 without it.
and 8 more in the full report
8 fixed6 passed either way5 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When invoking the ClinicalTrials.gov search tool `search_clinical_trials` for a disease-only search, developers often pass only the disease string under condition. What parameter is strictly required to avoid an API error, and what exact value must the action parameter take?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies query_term as a required parameter even when filtering by condition. | Missed | Passed |
| Requires setting the action parameter value to search_studies. | Missed | Passed |
The instructions your model reads when the skill loads.
Transform patient molecular profiles and clinical characteristics into prioritized clinical trial recommendations. Searches ClinicalTrials.gov and cross-references with molecular databases (CIViC, OpenTargets, ChEMBL, FDA) to produce evidence-graded, scored trial matches.
KEY PRINCIPLES:
Match patients to trials by molecular profile FIRST (specific mutations), then by disease stage, then by prior treatments. A patient with EGFR L858R should match to EGFR-targeted trials regardless of other factors. 4. Evidence-graded - Every recommendation has an evidence tier (T1-T4) 5. Quantitative scoring - Trial Match Score (0-100) for every trial 6. Eligibility-aware - Parse and evaluate inclusion/exclusion criteria 7. Actionable output - Clear next steps, contact info, enrollment status 8. Source-referenced - Every statement cites the tool/database source 9. Completeness checklist - Mandatory section showing analysis coverage 10. English-first queries - Always use English terms in tool calls. Respond in user's language
When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.
Apply when user asks:
test cases passed, vs 6 / 14 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.