aizech/clinical-skills / skills/platform-integration/pubmed-search
pubmed-search
VerifiedEvidence-based literature search for radiology. Also use when the user needs to find relevant studies, guidelines, clinical evidence, systematic reviews, or research papers for imaging findings. For guideline-specific searches, see guideline-integration.
| File | Kind | Size |
|---|---|---|
| SKILL-Computer.md | markdown | 9.0 KB |
| SKILL.md | skill md | 9.0 KB |
| evals/evals-Computer.json | config | 2.3 KB |
| evals/evals.json | config | 2.3 KB |
evals/evals-Computer.json
View on GitHub{
"tests": [
{
"id": "basic-lung-nodule-search",
"input": "Search for recent literature on lung nodule detection AI",
"expected": {
"action": "pubmed_search",
"query_terms": ["lung nodule", "detection", "AI"],
"date_filter": "recent"
}
},
{
"id": "specific-guideline-search",
"input": "Find ACR guidelines for incidental pulmonary nodules",
"expected": {
"action": "pubmed_search",
"query_terms": ["ACR", "incidental pulmonary nodules", "guidelines"],
"source_preference": "guidelines"
}
},
{
"id": "filter-by-year",
"input": "Search for COVID-19 chest X-ray AI studies from 2024",
"expected": {
"action": "pubmed_search",
"query_terms": ["COVID-19", "chest X-ray", "AI"],
"year": 2024
}
},
{
"id": "clinical-trial-search",
"input": "Find clinical trials for AI-assisted mammography screening",
"expected": {
"action": "clinical_trial_search",
"query_terms": ["mammography", "AI", "screening"]
}
},
{
"id": "systematic-review",
"input": "Find systematic reviews on deep learning in radiology",
"expected": {
"action": "pubmed_search",
"query_terms": ["deep learning", "radiology"],
"article_type": "systematic review"
}
},
{
"id": "guideline-integration",
"input": "What are the current guidelines for lung cancer screening CT?",
"expected": {
"action": "guideline_search",
"query_terms": ["lung cancer screening", "guidelines"]
}
},
{
"id": "citation-count-filter",
"input": "Find highly cited papers on radiology AI from the last 5 years",
"expected": {
"action": "pubmed_search",
"query_terms": ["radiology", "AI"],
"min_citations": "high",
"years_back": 5
}
},
{
"id": "comparison-studies",
"input": "Compare AI vs radiologist performance in mammography",
"expected": {
"action": "pubmed_search",
"query_terms": ["mammography", "AI", "radiologist", "comparison"]
}
}
],
"criteria": {
"pass_rate": "All tests must pass",
"query_construction": "Properly construct PubMed search queries",
"result_relevance": "Return relevant results"
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |