Agent skill

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.

foryourhealth111-pixelgithub.com/foryourhealth111-pixelGitHub ↗
claude-codecodexcan modify filesships scriptsApache-2.0
Install
npx skills add foryourhealth111-pixel/Vibe-Skills --skill clinical-decision-support --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 20
SKILL.md size: 26 KB
Bundled scripts: yes
Allowed tools: ReadWriteEditBash
Path: bundled/skills/clinical-decision-support/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 2,593
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Generates professional clinical decision support documents for pharmaceutical companies, clinical researchers, and medical decision-makers, specializing in two main outputs: (1) patient cohort analyses with biomarker stratification and statistical outcomes, and (2) treatment recommendation reports with GRADE grading and decision algorithms. All outputs are publication-ready LaTeX/PDF optimized for drug development, clinical research, and evidence synthesis. It includes a note to use a separate skill for individual patient plans.

How it works

The skill covers two document types: Patient Cohort Analysis and Treatment Recommendation Reports. It supports biomarker integration (mutations, CNV, fusions, gene expression, IHC, PD-L1), survival and hazard analyses (OS, PFS, HRs, Kaplan-Meier, log-rank, Cox), and evidence grading (GRADE, Oxford CEBM). It generates structured sections and visuals, including decision algorithms and flowcharts (TikZ), and requires publication-ready formatting with 0.5-inch margins. It mandates mandatory figures via the scientific-schematics approach, using the dedicated tool to create one or more diagrams, and outputs must be in LaTeX/PDF format suitable for regulatory submissions and guideline development. It explicitly instructs to begin pages with a complete executive summary on page 1, using colored tcolorbox blocks for key findings.

When to use it

Use this skill to analyze cohorts stratified by biomarkers or molecular subtypes, generate treatment recommendation reports with GRADE-based recommendations, compare subgroup outcomes with survival and response metrics, and produce pharmaceutical/research documents for drug development, trials, or regulatory submissions. It is not intended for individual bedside treatment planning.

What it can touch

The skill lists allowed-tools: Read, Write, Edit, Bash. It declares access to claude-code and codex as tools for execution. It requires generation of publication-ready LaTeX/PDF outputs and TikZ-based diagrams, with figures produced via the scientific-schematics workflow. It references integration with tools for citation management, statistical reporting, and schematic generation, but explicit file paths or script invocations beyond the schematic generation example are not provided in this summary.

Caveats

License: Apache-2.0. The skill emphasizes population-level analyses and guideline development, with integration of regulatory considerations (HIPAA de-identification, ICH-GCP alignment). It notes that a separate treatment-plans skill should be used for individual patient treatment plans. It enforces the mandatory page-1 executive summary structure and the inclusion of AI-generated figures via the scientific-schematics process. Explicit outcomes are contingent on data and analyses performed by the user; the skill does not guarantee specific results.

From the SKILL.md

# 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 statistica

More from Vibe-Skills
All skills →
About this skill
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 foryourhealth111-pixel/Vibe-Skills --skill clinical-decision-support --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 foryourhealth111-pixel/Vibe-Skills, a repository with 2,593 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.

Keep going