clinical-decision-support

Generate evidence-based clinical decision support documents with GRADE grading and survival analysis.

5|2|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/hyperbolic-c/auto-writing --skill clinical-decision-support-hyperbolic-c
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clinical-decision-support
Source: https://github.com/hyperbolic-c/auto-writing/tree/main/claude-scientific-writer/skills/clinical-decision-support
Command: npx skills add https://github.com/hyperbolic-c/auto-writing --skill clinical-decision-support-hyperbolic-c

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, lifelines, matplotlib, pyyaml, scikit-learn, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill standardizes the creation of population-level analyses and evidence-based clinical decision support documents for pharmaceutical research, enabling consistent guideline development and regulatory submissions.

Core Features & Use Cases

  • Biomarker-guided cohort analyses with survival statistics (OS, PFS, HR) and subgroup comparisons
  • GRADE-based treatment recommendations with explicit evidence grading and decision algorithms
  • TikZ-based clinical decision algorithms, flowcharts, and clinical pathway diagrams
  • Publication-ready LaTeX templates and narrative reports for regulatory submissions and medical affairs
  • Use Case: Generate a multi-biomarker cohort report with survival curves, forest plots, and evidence tables for a targeted therapy

Quick Start

  • Provide a disease area and patient cohort; the tool will generate a CDS document skeleton with sections for executive summary, methods, results, and references.

Frequently Asked Questions about clinical-decision-support

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a clinical decision support document with GRADE grading and survival analysis?

To generate a clinical decision support document, provide a disease area and patient cohort to produce a LaTeX report skeleton featuring GRADE-based recommendations, Kaplan-Meier survival curves, and evidence tables.

Can I create biomarker-guided cohort analyses with Kaplan-Meier curves for oncology research?

Yes, you can create biomarker-guided cohort analyses for oncology and cardiovascular domains that calculate survival statistics like OS and PFS, generate Kaplan-Meier curves, and perform subgroup comparisons.

Does this clinical decision support tool produce publication-ready LaTeX reports for regulatory submissions?

Yes, the tool produces publication-ready LaTeX templates and narrative reports designed specifically for pharmaceutical research, medical affairs, and regulatory submission workflows.

How do I add clinical decision algorithms and flowcharts to a pharmacological guideline report?

You can add clinical decision algorithms and flowcharts by utilizing the integrated TikZ support to generate structured clinical pathway diagrams and decision trees directly within the LaTeX report.

What dependencies are needed to run survival analysis and evidence synthesis workflows?

You need pandas, numpy, scipy, lifelines, matplotlib, pyyaml, and scikit-learn installed to support the statistical computations, survival analysis modeling, and data processing workflows.

What is the best way to structure evidence-based treatment recommendations for a targeted therapy?

The best way to structure evidence-based recommendations is using the GRADE grading framework, which provides explicit evidence grading and decision algorithms for multi-biomarker cohort reports.