agentleFS
aizechaizech/clinical-skills/.agents/skills/radiology-research/SKILL.md

radiology-research

Skill4 starsChanged 7 months agoMITView on GitHub

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.

The file

Files
SKILL.md

Radiology Research Skill

Triggers

  • "recent research on"
  • "literature review"
  • "published studies"
  • "evidence for"
  • "systematic review"
  • "clinical trials"
  • "accuracy metrics"
  • "what does the evidence say"

Parameters

  • research_type (required): Type of research query
    • recent_papers - Latest publications
    • evidence_summary - Synthesized evidence
    • accuracy_metrics - Performance benchmarks
    • guidelines_review - Professional society guidelines
    • clinical_trials - Ongoing trials
    • systematic_review - Comprehensive literature review
  • topic (required): Research topic or clinical question
  • time_range (optional): Publication date filter (e.g., last 2 years)
  • modality (optional): Specific imaging modality

Research Quality Levels

LevelEvidence Type
1Randomized controlled trials, meta-analyses
2Cohort studies, case-control
3Case series, expert opinion
4Anecdotal reports

Key Research Areas

AI/ML in Radiology

  • Diagnostic accuracy studies
  • Performance benchmarking
  • External validation results
  • Clinical implementation outcomes

Imaging Techniques

  • Protocol optimization
  • New sequence development
  • Contrast agent innovations
  • Dose reduction techniques

Clinical Applications

  • Screening effectiveness
  • Diagnostic accuracy by condition
  • Treatment monitoring
  • Prognostic imaging markers

Literature Sources

  • PubMed/MEDLINE (primary)
  • RSNA Radiology (journal)
  • Academic Radiology (journal)
  • European Radiology (journal)
  • arXiv (preprints)
  • ClinicalTrials.gov (trials)

Output Format

Returns structured JSON with:

  • Citation list with relevance scores
  • Key findings summary
  • Accuracy metrics (sensitivity, specificity, AUC)
  • Study quality indicators
  • Clinical applicability notes

Usage Examples

research_type: recent_papers
topic: deep learning chest X-ray pneumonia
time_range: last_2_years

research_type: evidence_summary
topic: MRI vs CT for appendicitis diagnosis
modality: CT, MRI

Integration

Links to:

  • pubmed-search for detailed literature access
  • guideline-integration for society recommendations
  • cross-reference-linking for related cases

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.