Skip to content

aizech/clinical-skills / skills/research-evidence/radiology-research

radiology-research

Verified

Access and synthesize medical imaging research literature. Use when user mentions "recent research on", "literature review", "published studies", "evidence for", or needs to find relevant research.

FileKindSize
SKILL-Computer.mdmarkdown2.4 KB
SKILL.mdskill md2.4 KB
evals/evals-Computer.jsonconfig1.8 KB
evals/evals.jsonconfig1.8 KB

evals/evals-Computer.json

View on GitHub
{
  "$evals": [
    {
      "id": "research-lung-ai",
      "prompt": "Find recent research papers on AI-based lung nodule detection published in the last 2 years. Include accuracy metrics and datasets used.",
      "expected": "Paper list with accuracy metrics, dataset details, and key methodology highlights.",
      "metrics": ["recency", "relevance", "metric_accuracy"]
    },
    {
      "id": "research-stroke-imaging",
      "prompt": "What is the current evidence for MRI diffusion imaging in acute stroke within the 6-hour window? Include key studies and recommendations.",
      "expected": "Evidence summary with key studies, sample sizes, and clinical recommendations.",
      "metrics": ["evidence_quality", "clinical_alignment"]
    },
    {
      "id": "research-pet-standards",
      "prompt": "Summarize current PET/CT reporting standards including PERCIST criteria for treatment response assessment.",
      "expected": "Standard summary with PERCIST criteria details and application guidance.",
      "metrics": ["standard_accuracy", "application_clarity"]
    },
    {
      "id": "research-contrast-safety",
      "prompt": "What is the latest evidence on gadolinium deposition in brain tissue from MRI contrast agents? What are current safety recommendations?",
      "expected": "Evidence summary with current guidelines, risk factors, and alternative recommendations.",
      "metrics": ["safety_focus", "currency"]
    },
    {
      "id": "research-systematic-review",
      "prompt": "Perform a systematic review search for AI accuracy in chest X-ray interpretation compared to radiologist performance.",
      "expected": "Structured review summary with study counts, pooled accuracy, and bias assessment.",
      "metrics": ["methodological_rigor", "comprehensiveness"]
    }
  ],
  "$skill": "research-evidence/radiology-research",
  "$version": "1.0.0"
}
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: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall