# clinical-note-extract-skill

The clinical-note-extract-skill skill extracts structured data from medical text with citations for each value and explicit markers for missing fields. Use it to build registries, check trial eligibility, and flag information gaps.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 127 installs · ★ 456 repo stars
- Author: anthropics · official Anthropic repository
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/anthropics/healthcare/tree/HEAD/plugins/healthcare/skills/clinical-note-extract/SKILL.md
- Updated: 2026-08-27
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/clinical-note-extract-skill

## What it does

The skill transforms unstructured clinical notes into structured records against a schema you define. Each value carries a citation from the source text, plus metadata about presence, temporality, and null reasons.

The workflow has four steps: you define a schema with field descriptions and validation rules, the skill extracts data from one or many notes in an isolated, tool-free mode, then runs deterministic validation—checking citations against the source and coding values against terminologies (SNOMED, LOINC, or others if you specify them), and finally produces a report showing which fields were populated, which are absent, and which failed checks.

For larger note sets, use the built-in `batch.ts` script, which processes files locally without sending clinical data to the API. Output records can export to FHIR resources (Condition, FamilyMemberHistory)—the mapping is deterministic and requires no model inference.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add anthropics/healthcare --skill clinical-note-extract-skill -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add anthropics/healthcare --skill clinical-note-extract-skill -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add anthropics/healthcare --skill clinical-note-extract-skill -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install anthropics/healthcare plugins/healthcare/skills/clinical-note-extract
```

2. **Manually: put the files in place**
- File: `.github/skills/clinical-note-extract/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add anthropics/healthcare --skill clinical-note-extract-skill -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/anthropics/healthcare --path plugins/healthcare/skills/clinical-note-extract
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add anthropics/healthcare --skill clinical-note-extract-skill -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/anthropics/healthcare/tree/HEAD/plugins/healthcare/skills/clinical-note-extract/SKILL.md

## When to use it
- extract structured clinical data with source citations
- build a patient registry from unstructured notes
- screen patients against trial inclusion criteria
- code clinical findings to SNOMED or LOINC
- convert flat records to FHIR resources

## Example prompts
- Pull age, diagnosis, and current medications from this note with paragraph citations
- Build a registry from 50 notes: patient ID, birthdate, complications, smoking status
- Find patients for a study: age 18–65, type 2 diabetes, no chronic kidney disease

## Similar
- [tooluniverse-clinical-risk-scoring](https://affpapa.org/en/nevibecode/skills/tooluniverse-clinical-risk-scoring.md) — skill · 125 installs
- [clinical-diagnostic-reasoning](https://affpapa.org/en/nevibecode/skills/clinical-diagnostic-reasoning.md) — skill · 178 installs
- [FHIR MCP Server](https://affpapa.org/en/nevibecode/mcp/fhir-mcp-server.md) — MCP server · ★ 139 repo stars
- [brief](https://affpapa.org/en/nevibecode/skills/insilico-org-brief.md) — skill · ★ 93 repo stars
- [healthcare-expert](https://affpapa.org/en/nevibecode/skills/healthcare-expert.md) — skill · 443 installs
- [appendix](https://affpapa.org/en/nevibecode/mcp/appendix-appendix.md) — MCP server · 665 installs

From the same set: [anthropics/healthcare](https://affpapa.org/en/nevibecode/by/anthropics/healthcare.md) — 9 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
