# domain-research-health-science

domain-research-health-science structures health science and medical evidence synthesis using PICOT framing, formal bias checklists, and GRADE certainty scoring.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 119 installs · ★ 203 repo stars
- Author: lyndonkl
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lyndonkl/claude/tree/HEAD/skills/domain-research-health-science/SKILL.md
- Updated: 2026-09-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/domain-research-health-science

## What it does

The skill guides assistants through a six-step workflow for health science literature review. It begins with explicit PICOT structuring and matches inquiry types to corresponding study architectures, selecting randomized trials for therapies or cohort studies for prognosis.

Bias appraisal uses recognized domain benchmarks: Cochrane RoB 2 for randomized trials, ROBINS-I for observational cohorts, and QUADAS-2 for diagnostic tests. It prioritizes endpoints that matter directly to patients over laboratory surrogates, establishing minimal clinically important differences before synthesising evidence.

Synthesized outputs follow GRADE criteria down to final certainty ratings. The bundled validation rubric enforces an average score threshold of at least 3.5, which blocks superficial reviews that skip confounder analysis.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill domain-research-health-science -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/domain-research-health-science/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/domain-research-health-science/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill domain-research-health-science -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/domain-research-health-science/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill domain-research-health-science -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/domain-research-health-science/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/domain-research-health-science
```

2. **Manually: put the files in place**
- File: `.github/skills/domain-research-health-science/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill domain-research-health-science -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/domain-research-health-science
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/domain-research-health-science/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill domain-research-health-science -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/lyndonkl/claude/tree/HEAD/skills/domain-research-health-science/SKILL.md

## When to use it
- structure clinical inquiries using the PICOT framework
- assess trial risk of bias with Cochrane RoB 2 or ROBINS-I
- separate patient-critical endpoints from laboratory surrogate markers
- rate evidence certainty using standardized GRADE criteria

## Example prompts
- Structure a PICOT question comparing SGLT2 inhibitors against standard care for heart failure
- Evaluate this observational study for risk of bias using ROBINS-I criteria
- Generate a summary of findings table and assign GRADE certainty ratings to these outcomes

## Similar
- [life-science-research](https://affpapa.org/en/nevibecode/plugins/life-science-research.md) — plugin · ★ 8052 repo stars
- [clinical-decision-support](https://affpapa.org/en/nevibecode/skills/k-dense-ai-clinical-decision-support.md) — skill · 2100 installs
- [medical-research](https://affpapa.org/en/nevibecode/skills/medical-research.md) — skill · 673 installs
- [research-ops-skills](https://affpapa.org/en/nevibecode/plugins/research-ops-skills.md) — plugin · ★ 30251 repo stars
- [clinical-research](https://affpapa.org/en/nevibecode/skills/clinical-research.md) — skill · 156 installs
- [scientific-critical-thinking](https://affpapa.org/en/nevibecode/skills/k-dense-ai-scientific-critical-thinking.md) — skill · 2600 installs

From the same set: [lyndonkl/claude](https://affpapa.org/en/nevibecode/by/lyndonkl/claude.md) — 49 cards

---
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
