clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
npx skills add majiayu000/claude-skill-registry --skill clinical-decision-support-hxk622-tokendance-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates professional clinical decision support documents for pharmaceutical and clinical research settings, focusing on group-level analyses (patient cohorts) and evidence-based treatment recommendations. Documents are publication-ready LaTeX/PDF files optimized for drug development, regulatory submissions, and guideline development.
How it works
- Produces two document types: (1) Patient Cohort Analysis with biomarker stratification, survival analyses, and waterfall plots; (2) Treatment Recommendation Reports with GRADE grading and decision algorithms.
- Includes biomarker integration (genomic alterations, IHC, PD-L1, etc.), statistical analyses (hazard ratios, p-values, confidence intervals, Kaplan-Meier analyses), and regulatory-compliance considerations (HIPAA de-identification, ICH-GCP alignment).
- Outputs publication-ready LaTeX/PDF, with guidance on structured abstracts, CONSORT/STROBE alignment, and publication formatting.
- Requires schematic figures generated via the scientific-schematics workflow, including at least 1-2 AI-generated figures per document.
- Designed for group-level analyses in pharmaceutical development, real-world evidence, and guideline development.
When to use it
- When you need biomarker-stratified cohort analyses or treatment recommendation reports with GRADE grading.
- When generating documents for regulatory submissions, guidelines development, or publication planning.
- When synthesizing evidence across trials or real-world cohorts and presenting flowcharts, Kaplan-Meier curves, forest plots, and waterfall analyses.
What it can touch
- Tools: code_execute, web_search, read_url, create_document are declared as allowed tools.
- It supports integration of cohort analyses, biomarker data, and evidence grading within LaTeX/PDF outputs suitable for publication and regulatory packages.
Caveats
- Emphasizes publication-ready formatting (LaTeX/PDF); individual bedside treatment plans should use the treatment-plans skill.
- Requires generation of AI-produced figures via the scientific-schematics skill; at least 1-2 figures must be produced per document.
- The skill notes HIPAA de-identification and regulatory alignment; it does not specify outcomes beyond the stated capabilities.
# Clinical Decision Support Documents ## Description Generate professional clinical decision support (CDS) documents for pharmaceutical companies, clinical researchers, and medical decision-makers. This skill specializes in analytical, evidence-based documents that inform treatment strategies and drug development: 1. **Patient Cohort Analysis** - Biomarker-stratified group analyses with statistical outcome comparisons 2. **Treatment Recommendation Reports** - Evidence-based clinical guidelines with GRADE grading and decision algorithms All documents are generated as publication-ready LaTeX/PDF files optimized for pharmaceutical research, regulatory submissions, and clinical guideline development. **Note:** For individual patient treatment plans at the bedside, use the `treatment-plans` skill instead. This skill focuses on group-level analyses and evidence synthesis for pharmaceutical/research settings. **Writing Style:** For publication-ready documents targeting medical journals, consult the **venue-templates** skill's `medical_journal_styles.md` for guidance on structured abstracts, evidence language, and CONSORT/STROBE compliance. ## Capabilities ### Document Types **Patient Coho
- Description
- Capabilities
- Document Types
- Clinical Features
- Pharmaceutical and Research Use Cases
- When to Use
- Visual Enhancement with Scientific Schematics
- Document Structure
- Page 1 Executive Summary Structure
- Patient Cohort Analysis (Detailed Sections - Page 3+)
- Treatment Recommendation Reports (Detailed Sections - Page 3+)
- Output Format
- Integration
- Key Differentiators from Treatment-Plans Skill
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
What does the clinical-decision-support skill do?
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill clinical-decision-support-hxk622-tokendance-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.