abridge-reference-architecture
Implement Abridge reference architecture for clinical AI integration. Use when designing a new Abridge deployment, reviewing project structure, or planning multi-site health system rollouts with EHR integration. Trigger: "abridge architecture", "abridge project structure", "abridge system design", "abridge multi-site".
What this skill does
# Abridge Reference Architecture
## Overview
Reference architecture for Abridge clinical AI integration in a multi-site health system. Covers data flow, component design, EHR integration patterns, and HIPAA-compliant infrastructure.
## System Architecture
```
Health System Network
┌──────────────────────────────────────────────────────┐
│ │
│ ┌─────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Provider │───▶│ Abridge App │───▶│ Integration │ │
│ │ Device │ │ (Ambient AI) │ │ Service │ │
│ │ (mobile/ │ │ │ │ (your code) │ │
│ │ desktop) │ └──────┬───────┘ └──────┬───────┘ │
│ └─────────┘ │ │ │
│ │ │ │
│ ┌─────────▼─────────┐ │ │
│ │ Abridge Cloud API │ │ │
│ │ (Partner API) │ │ │
│ │ - Session mgmt │ │ │
│ │ - Note generation │ │ │
│ │ - Patient summary │ │ │
│ └─────────┬─────────┘ │ │
│ │ │ │
│ ┌─────────▼─────────┐ ┌──────▼───────┐ │
│ │ Webhook Events │ │ EHR System │ │
│ │ - Note completed │──│ (Epic/Athena)│ │
│ │ - Quality alerts │ │ FHIR R4 API │ │
│ └───────────────────┘ └──────────────┘ │
│ │
└──────────────────────────────────────────────────────┘
```
## Project Structure
```
abridge-integration/
├── src/
│ ├── config/
│ │ ├── abridge.ts # Abridge API configuration
│ │ ├── ehr.ts # EHR/FHIR endpoint config
│ │ └── index.ts # Environment-based config loader
│ ├── abridge/
│ │ ├── client.ts # API client singleton
│ │ ├── errors.ts # HIPAA-safe error handling
│ │ ├── retry.ts # Retry with backoff
│ │ └── session-manager.ts # Encounter session lifecycle
│ ├── ehr/
│ │ ├── fhir-client.ts # FHIR R4 API wrapper
│ │ ├── epic-adapter.ts # Epic-specific mappings
│ │ ├── athena-adapter.ts # Athena-specific mappings
│ │ └── note-pusher.ts # DocumentReference creation
│ ├── webhooks/
│ │ ├── handler.ts # Express webhook endpoint
│ │ ├── signature.ts # HMAC signature verification
│ │ ├── event-router.ts # Event type → handler mapping
│ │ └── idempotency.ts # Duplicate event prevention
│ ├── security/
│ │ ├── audit-logger.ts # HIPAA audit trail
│ │ ├── phi-redactor.ts # PHI detection and redaction
│ │ ├── rbac.ts # Role-based access control
│ │ └── tls-config.ts # TLS 1.3 enforcement
│ ├── monitoring/
│ │ ├── health.ts # Health check endpoint
│ │ ├── metrics.ts # Performance metrics collector
│ │ └── alerts.ts # Quality and latency alerts
│ └── server.ts # Express server entry point
├── tests/
│ ├── unit/ # Unit tests (no API calls)
│ ├── integration/ # Sandbox API tests
│ └── fhir-validation/ # FHIR resource schema tests
├── fixtures/
│ └── transcripts/ # Synthetic encounter transcripts
├── scripts/
│ ├── deploy-cloud-run.sh # GCP Cloud Run deployment
│ ├── readiness-check.ts # Production readiness validation
│ └── diagnostic.sh # Debug data collection
├── Dockerfile # HIPAA-compliant container
├── .env.example # Environment template (no secrets)
└── package.json
```
## Key Design Decisions
| Decision | Choice | Rationale |
|----------|--------|-----------|
| Language | TypeScript | Type safety for healthcare data |
| EHR adapter | Strategy pattern | Swap EHR backends without changing core |
| Error handling | Custom error class | HIPAA-safe: never log PHI |
| Authentication | SMART on FHIR | Standard for healthcare OAuth |
| Deployment | Cloud Run | HIPAA BAA, auto-scaling, managed |
| Secrets | GCP Secret Manager | HIPAA-compliant, audited access |
| Monitoring | Custom health endpoint | Abridge + FHIR connectivity checks |
## Data Flow
```
1. Provider opens encounter on device
2. Abridge app captures ambient audio
3. Audio streams to Abridge Cloud via WebSocket
4. Real-time transcript fragments returned
5. Provider closes encounter
6. Abridge generates structured clinical note (10-30s)
7. Webhook fires: encounter.session.completed
8. Integration service fetches note via API
9. Note pushed to EHR via FHIR DocumentReference
10. Patient summary generated and pushed to portal
11. Provider reviews, edits, and signs note in EHR
12. Webhook fires: encounter.note.signed
```
## Multi-Site Deployment
```typescript
// src/config/multi-site.ts
interface SiteConfig {
siteId: string;
siteName: string;
ehrType: 'epic' | 'athena' | 'cerner';
fhirBaseUrl: string;
abridgeOrgId: string;
specialties: string[];
providerCount: number;
goLiveDate: Date;
}
const sites: SiteConfig[] = [
{
siteId: 'main-campus',
siteName: 'Main Hospital',
ehrType: 'epic',
fhirBaseUrl: 'https://fhir.main-hospital.epic.com/interconnect-fhir-oauth',
abridgeOrgId: 'org_main_campus',
specialties: ['internal_medicine', 'cardiology', 'pulmonology'],
providerCount: 200,
goLiveDate: new Date('2026-06-01'),
},
{
siteId: 'community-clinic',
siteName: 'Community Clinic Network',
ehrType: 'athena',
fhirBaseUrl: 'https://api.athenahealth.com/fhir/r4',
abridgeOrgId: 'org_community',
specialties: ['family_medicine', 'pediatrics'],
providerCount: 50,
goLiveDate: new Date('2026-09-01'),
},
];
```
## Output
- Complete project structure for Abridge integration
- EHR adapter pattern supporting Epic, Athena, and Cerner
- Multi-site deployment configuration
- End-to-end data flow documentation
## Resources
- [Abridge Platform](https://www.abridge.com/product)
- [Abridge Clinician App](https://www.abridge.com/platform/clinicians)
- [FHIR R4 Specification](https://hl7.org/fhir/R4/)
- [Epic FHIR APIs](https://fhir.epic.com/)
- [GCP Healthcare API](https://cloud.google.com/healthcare-api)
## Next Steps
Start implementation with `abridge-install-auth`, then follow the skill sequence through production deployment.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.