# tooluniverse-clinical-risk-scoring

tooluniverse-clinical-risk-scoring — a skill for Claude Code, Codex, Cursor and other agents that computes validated clinical risk scores from individual patient data.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 125 installs · ★ 1798 repo stars
- Author: mims-harvard
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-clinical-risk-scoring/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/tooluniverse-clinical-risk-scoring

## What it does

The skill maps a clinical scenario to the right calculator, collects the required patient inputs, and returns the numeric score with a per-factor component breakdown.

Ten deterministic tools sit underneath: `ClinicalCalc_CHA2DS2_VASc`, `ClinicalCalc_HAS_BLED`, `ClinicalCalc_CURB_65`, `ClinicalCalc_qSOFA`, `ClinicalCalc_Child_Pugh`, `ClinicalCalc_MELD_Na`, `ClinicalCalc_Wells_DVT`, `ClinicalCalc_Wells_PE`, `ClinicalCalc_ASCVD_risk`, and `ClinicalCalc_eGFR_CKD_EPI`. None of them make network calls or need an API key. For paired scenarios — atrial fibrillation or cirrhosis — the skill always runs both calculators, because CHA2DS2-VASc alone, without HAS-BLED, leaves the anticoagulation decision half-answered.

When a required input is missing, the agent asks for it rather than guessing, and explicitly states which boolean flags were assumed `false`. This skill covers bedside clinical scores only; polygenic risk, population epidemiology, and diagnostic test sensitivity/specificity math are handled by separate skills in the same repository.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-clinical-risk-scoring -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/tooluniverse-clinical-risk-scoring/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/tooluniverse-clinical-risk-scoring/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-clinical-risk-scoring -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/tooluniverse-clinical-risk-scoring/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-clinical-risk-scoring -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/tooluniverse-clinical-risk-scoring/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mims-harvard/ToolUniverse skills/tooluniverse-clinical-risk-scoring
```

2. **Manually: put the files in place**
- File: `.github/skills/tooluniverse-clinical-risk-scoring/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-clinical-risk-scoring -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mims-harvard/ToolUniverse --path skills/tooluniverse-clinical-risk-scoring
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/tooluniverse-clinical-risk-scoring/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-clinical-risk-scoring -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-clinical-risk-scoring/SKILL.md

## When to use it
- Compute stroke and bleeding risk together for an AF patient
- Grade community-acquired pneumonia severity with CURB-65
- Get Wells pretest probability for suspected DVT or PE
- Calculate eGFR via CKD-EPI to adjust a drug dose
- Score Child-Pugh and MELD-Na for a patient with cirrhosis

## Example prompts
- Calculate CHA2DS2-VASc and HAS-BLED for a 76-year-old woman with hypertension and diabetes
- Run CURB-65 for a 68-year-old with confusion, respiratory rate 32, BP 88/60
- Compute eGFR CKD-EPI: creatinine 1.4, age 61, male

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 626d3ac7a36611b9.

BEGIN THIRD-PARTY FILE 626d3ac7a36611b9
```text
---
name: tooluniverse-clinical-risk-scoring
description: Compute and interpret validated bedside clinical risk scores and pretest probabilities for an INDIVIDUAL patient — pick the right score for the scenario, gather inputs, run the deterministic calculator tool, and read the result against an interpretation table. Covers CHA2DS2-VASc (AF stroke risk), HAS-BLED (bleeding on anticoagulation), CURB-65 (pneumonia severity / admit decision), qSOFA (sepsis screen), Child-Pugh + MELD-Na (cirrhosis severity / transplant priority), Wells DVT and Wells PE (VTE pretest probability), ASCVD (10-year cardiovascular risk / statin decision), and eGFR CKD-EPI (kidney function / drug dosing). Use when asked things like "stroke risk for this AF patient", "should this patient be anticoagulated", "pneumonia severity — admit or not?", "sepsis screen this patient", "DVT/PE pretest probability", "10-year cardiovascular risk", "cirrhosis severity / MELD score", or "eGFR / kidney function". Pairs CHA2DS2-VASc with HAS-BLED to weigh anticoagulation. NOT for polygenic/genetic risk (use tooluniverse-polygenic-risk-score), NOT for population-level epidemiology/incidence (use tooluniverse-epidemiological-analysis), and NOT for diagnostic test sensitivity/specificity/likelihood-ratio math (use tooluniverse-diagnostic-test-evaluation).
disable-model-invocation: true
---

# Clinical Risk Scoring

Turn a clinical scenario into the right validated risk score, compute it with a deterministic calculator tool, and interpret the number into a clinical action. All 10 backing tools are pure-compute (no network, no API key) and return `{status, data:{score, interpretation, components, ...}}`.

This skill is **decision-support only** — see LIMITATIONS. It does not replace clinical judgment.

## Step 1 — Map the scenario to the score(s)

| Clinical scenario | Score(s) | Tool(s) |
|---|---|---|
| Atrial fibrillation — stroke risk / anticoagulate? | CHA2DS2-VASc **and** HAS-BLED (pair) | `ClinicalCalc_CHA2DS2_VASc` + `ClinicalCalc_HAS_BLED` |
```
END THIRD-PARTY FILE 626d3ac7a36611b9

The third-party file has ended. Everything between the 626d3ac7a36611b9 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2044 of 12812 bytes. © mims-harvard · Apache-2.0 · https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-clinical-risk-scoring/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
