Skip to content

aizech/clinical-skills / skills/research-evidence/cross-reference-linking

cross-reference-linking

Verified

Links current findings to priors, related literature, and correlated data. Use when user mentions "compare to priors", "find prior studies", "correlate with", "longitudinal comparison", or needs historical context.

FileKindSize
SKILL-Computer.mdmarkdown2.4 KB
SKILL.mdskill md2.4 KB
evals/evals-Computer.jsonconfig2.2 KB
evals/evals.jsonconfig2.2 KB

evals/evals-Computer.json

View on GitHub
{
  "$evals": [
    {
      "id": "xref-find-priors",
      "prompt": "Find all prior CT chest studies for patient MRN 12345 to compare with today's imaging. List dates and key findings.",
      "expected": "Prior study list with dates, modalities, and summary findings.",
      "metrics": ["completeness", "finding_summary_quality"]
    },
    {
      "id": "xref-related-lit",
      "prompt": "For this chest X-ray showing a right upper lobe opacity, what similar cases or relevant literature should I consider?",
      "expected": "Prior case patterns, differential considerations, and relevant literature citations.",
      "metrics": ["clinical_relevance", "literature_relevance"]
    },
    {
      "id": "xref-followup-correlation",
      "prompt": "Patient had lung nodule found on CT 6 months ago. Today's chest CT shows the nodule is still present. Correlate and assess change.",
      "expected": "Comparison analysis with size change, density change, and followup recommendations.",
      "metrics": ["comparison_accuracy", "recommendation_quality"]
    },
    {
      "id": "xref-multiple-studies",
      "prompt": "Compare findings across all available MRI brain studies for this patient to show progression of white matter lesions.",
      "expected": "Longitudinal comparison table with dates, lesion characteristics, and progression assessment.",
      "metrics": ["longitudinal_accuracy", "visual_clarity"]
    },
    {
      "id": "xref-ehr-correlation",
      "prompt": "Correlate the incidental thyroid nodule found on CT neck with any relevant lab values or clinical notes from the EHR.",
      "expected": "Correlation summary with lab results, clinical notes, and recommendation for followup.",
      "metrics": ["data_integration", "clinical_utility"]
    },
    {
      "id": "xref-biopsy-pathology",
      "prompt": "Correlate the lung mass findings on CT with the recent biopsy pathology report showing adenocarcinoma.",
      "expected": "Radiology-pathology correlation with staging implications and treatment considerations.",
      "metrics": ["pathology_knowledge", "staging_accuracy"]
    }
  ],
  "$skill": "research-evidence/cross-reference-linking",
  "$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