Skills clinical-decision-support

📊

clinical-decision-support

Name: clinical-decision-support
Author: K-Dense-AI

Safe 📁 Filesystem access

Generate Clinical Decision Support Documents

Also available from: davila7

Clinical researchers need evidence-based documents for drug development and regulatory submissions. This skill creates publication-ready clinical decision support documents with biomarker stratification and GRADE evidence grading.

Supports: Claude Codex Code(CC)

🥈 80 Silver

Download the skill ZIP

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

Toggle on and start using

Test it

Using "clinical-decision-support". Analyze 60 HER2+ breast cancer patients by hormone receptor status with trastuzumab-deruxtecan outcomes

Expected outcome:

Executive Summary: HR+/HER2+ vs HR-/HER2+ efficacy comparison
Demographics table with baseline characteristics
ORR: 68% vs 78% (p=0.041) favoring HR-negative
Median PFS: 16.2 vs 22.1 months (HR=0.74, 95% CI: 0.58-0.95)
Kaplan-Meier survival curves with 95% confidence bands
Forest plot showing subgroup analyses
Clinical implications with Grade 1A recommendation

Using "clinical-decision-support". Create treatment recommendations for first-line EGFR-mutant NSCLC with osimertinib

Expected outcome:

Strong recommendation for osimertinib 80mg daily (Grade 1A)
Evidence from FLAURA trial: PFS 18.9 vs 10.2 months (HR 0.46)
OS benefit: 38.6 vs 31.8 months (HR 0.80, p=0.046)
Treatment algorithm flowchart with biomarker decision points
Adverse event profile and monitoring requirements

Security Audit

Safe

v4 • 1/17/2026

All static findings are false positives. The skill generates legitimate clinical research documents using standard Python libraries (pandas, numpy, scipy). The 'weak cryptographic algorithm' detections are medical terminology matches (e.g., hazard ratio, recommendation strength). 'External commands' flagged are markdown backticks for documentation formatting, not shell execution. Filesystem operations are standard document generation. No malicious code, credential exfiltration, or harmful patterns exist.

Files scanned

9,010

Lines analyzed

findings

Total audits

Risk Factors

📁 Filesystem access (3)

scripts/build_decision_tree.py:221 scripts/create_cohort_tables.py:464 scripts/generate_survival_analysis.py:286

Audited by: claude View Audit History →

Quality Score

Architecture

100

Maintainability

Content

Community

100

Security

Spec Compliance

What You Can Build

Drug Development Documentation

Generate biomarker-stratified cohort analyses for Phase 2/3 trials and regulatory submissions

Evidence-Based Guidelines

Create treatment recommendation reports with GRADE grading for medical societies

Submission Documents

Produce publication-ready analyses for IND/NDA submissions and advisory boards

Try These Prompts

Basic Cohort Analysis

Create a cohort analysis for 50 NSCLC patients stratified by PD-L1 expression levels. Include ORR, median PFS, and OS with hazard ratios comparing groups.

Treatment Guidelines

Generate GRADE-graded treatment recommendations for HER2+ metastatic breast cancer including first-line and subsequent therapies.

Biomarker Integration

Analyze 75 GBM patients by molecular subtype with outcomes, biomarker profiles, and treatment response comparison.

Decision Algorithm

Create a TikZ flowchart for advanced NSCLC treatment decisions based on PD-L1, EGFR, ALK, and performance status with recommendations.

Best Practices

Always include a complete executive summary on page 1 with 3-5 key findings in colored boxes
Use standard medical terminology and include trial names for evidence citations
Document statistical methods and include hazard ratios with 95% confidence intervals

Avoid

Do not include identifiable patient information - use de-identified data only
Avoid narrative text without data - support all recommendations with evidence tables
Do not skip the visual elements - include Kaplan-Meier curves and decision flowcharts