adobe-reference-architecture
Implement Adobe reference architecture for production integrations covering Firefly Services, PDF Services, I/O Events, and App Builder with layered project layout, error boundaries, and health monitoring. Trigger with phrases like "adobe architecture", "adobe project structure", "how to organize adobe", "adobe layout", "adobe best practices".
Best use case
adobe-reference-architecture is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Implement Adobe reference architecture for production integrations covering Firefly Services, PDF Services, I/O Events, and App Builder with layered project layout, error boundaries, and health monitoring. Trigger with phrases like "adobe architecture", "adobe project structure", "how to organize adobe", "adobe layout", "adobe best practices".
Teams using adobe-reference-architecture should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/adobe-reference-architecture/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How adobe-reference-architecture Compares
| Feature / Agent | adobe-reference-architecture | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Implement Adobe reference architecture for production integrations covering Firefly Services, PDF Services, I/O Events, and App Builder with layered project layout, error boundaries, and health monitoring. Trigger with phrases like "adobe architecture", "adobe project structure", "how to organize adobe", "adobe layout", "adobe best practices".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Adobe Reference Architecture
## Overview
Production-ready architecture patterns for Adobe API integrations, designed around the three main API families: Firefly Services (creative AI), PDF Services (document automation), and I/O Events (event-driven).
## Prerequisites
- Understanding of layered architecture
- TypeScript project setup
- Decision on which Adobe APIs to integrate
## Instructions
### Step 1: Project Structure
```
my-adobe-project/
├── src/
│ ├── adobe/ # Adobe client layer
│ │ ├── auth.ts # OAuth Server-to-Server token management
│ │ ├── firefly-client.ts # Firefly API wrapper (generate, fill, expand)
│ │ ├── pdf-client.ts # PDF Services wrapper (create, extract, merge)
│ │ ├── photoshop-client.ts # Photoshop API wrapper (cutout, actions)
│ │ ├── events-client.ts # I/O Events registration and verification
│ │ ├── types.ts # Shared Adobe types
│ │ └── errors.ts # Error classification (retryable vs permanent)
│ ├── services/ # Business logic layer
│ │ ├── image-generation.ts # Orchestrates Firefly + Photoshop workflows
│ │ ├── document-pipeline.ts # Orchestrates PDF create/extract/merge
│ │ └── event-processor.ts # Routes and processes I/O Events
│ ├── api/ # API layer (routes, controllers)
│ │ ├── health.ts # Health check including Adobe IMS
│ │ ├── webhooks/adobe.ts # I/O Events webhook endpoint
│ │ └── routes/
│ │ ├── images.ts # Image generation endpoints
│ │ └── documents.ts # Document processing endpoints
│ ├── jobs/ # Background job layer
│ │ ├── firefly-batch.ts # Batch image generation queue
│ │ └── pdf-extraction.ts # Async PDF extraction worker
│ └── index.ts
├── tests/
│ ├── unit/
│ │ ├── adobe/auth.test.ts
│ │ └── services/
│ └── integration/
│ └── adobe/
│ ├── firefly.test.ts
│ └── pdf-services.test.ts
├── config/
│ ├── adobe.development.json
│ ├── adobe.staging.json
│ └── adobe.production.json
└── package.json
```
### Step 2: Layer Architecture
```
┌─────────────────────────────────────────────────────┐
│ API Layer │
│ Routes, Controllers, Webhook Endpoints │
├─────────────────────────────────────────────────────┤
│ Service Layer │
│ Business Logic, Workflow Orchestration │
│ (image-generation.ts, document-pipeline.ts) │
├─────────────────────────────────────────────────────┤
│ Adobe Client Layer │
│ auth.ts, firefly-client.ts, pdf-client.ts │
│ Token caching, retry, error classification │
├─────────────────────────────────────────────────────┤
│ Infrastructure Layer │
│ Cache (LRU/Redis), Queue (BullMQ), Monitoring │
└─────────────────────────────────────────────────────┘
```
**Rules:**
- API layer never calls Adobe APIs directly — always through Service layer
- Service layer orchestrates multiple Adobe clients (e.g., Firefly + Photoshop)
- Adobe Client layer handles auth, retry, error classification
- Infrastructure layer is swappable (in-memory cache for dev, Redis for prod)
### Step 3: Error Boundary
```typescript
// src/adobe/errors.ts
export class AdobeServiceError extends Error {
constructor(
message: string,
public readonly code: string,
public readonly httpStatus: number,
public readonly retryable: boolean,
public readonly api: 'firefly' | 'pdf-services' | 'photoshop' | 'events',
public readonly retryAfter?: number,
public readonly originalError?: Error
) {
super(message);
this.name = 'AdobeServiceError';
}
static fromResponse(api: string, status: number, body: string, headers?: Headers): AdobeServiceError {
const retryAfter = headers?.get('Retry-After');
return new AdobeServiceError(
`Adobe ${api} API error (${status}): ${body.slice(0, 200)}`,
status === 429 ? 'RATE_LIMITED' :
status === 401 ? 'AUTH_EXPIRED' :
status >= 500 ? 'SERVER_ERROR' : 'CLIENT_ERROR',
status,
status === 429 || status >= 500,
api as any,
retryAfter ? parseInt(retryAfter) : undefined,
);
}
}
```
### Step 4: Configuration Management
```typescript
// config/adobe.ts
export interface AdobeConfig {
clientId: string;
clientSecret: string;
scopes: string;
environment: 'development' | 'staging' | 'production';
apis: {
firefly: { enabled: boolean; baseUrl: string };
pdfServices: { enabled: boolean };
photoshop: { enabled: boolean; baseUrl: string };
events: { enabled: boolean; webhookUrl: string };
};
retry: { maxRetries: number; baseDelayMs: number };
cache: { enabled: boolean; ttlSeconds: number };
}
export function loadConfig(): AdobeConfig {
const env = process.env.NODE_ENV || 'development';
const base = require(`./adobe.${env}.json`);
return {
...base,
clientId: process.env.ADOBE_CLIENT_ID!,
clientSecret: process.env.ADOBE_CLIENT_SECRET!,
scopes: process.env.ADOBE_SCOPES!,
environment: env as any,
};
}
```
### Step 5: Health Check
```typescript
// src/api/health.ts
export async function adobeHealthCheck(config: AdobeConfig) {
const checks: Record<string, any> = {};
// Always check IMS auth
try {
const start = Date.now();
await getCachedToken();
checks.ims = { status: 'healthy', latencyMs: Date.now() - start };
} catch (e: any) {
checks.ims = { status: 'unhealthy', error: e.message };
}
// Check enabled APIs
if (config.apis.firefly.enabled) {
checks.firefly = await pingEndpoint('https://firefly-api.adobe.io');
}
if (config.apis.photoshop.enabled) {
checks.photoshop = await pingEndpoint('https://image.adobe.io');
}
const overall = Object.values(checks).every(
(c: any) => c.status === 'healthy'
) ? 'healthy' : 'degraded';
return { status: overall, services: checks };
}
```
## Data Flow
```
User Request
│
▼
┌─────────────┐
│ Express │ ← Webhook from Adobe I/O Events
│ Router │
└──────┬───┬──┘
│ │
▼ ▼
┌────────┐ ┌────────────┐
│Service │ │Event │
│Layer │ │Processor │
└───┬────┘ └──────┬─────┘
│ │
▼ ▼
┌──────────────────────┐ ┌─────────┐
│ Adobe Client Layer │───▶│ Cache │
│ (auth + API calls) │ │ LRU/Redis│
└──────────┬───────────┘ └─────────┘
│
┌──────┼──────┐
▼ ▼ ▼
┌──────┐┌──────┐┌──────┐
│Firefly││PDF ││Photo │
│API ││Svc ││shop │
└──────┘└──────┘└──────┘
```
## Output
- Layered project structure separating concerns
- Error boundary with classification and retry logic
- Per-environment configuration with secret injection
- Health check covering IMS and all enabled APIs
## Resources
- [Adobe Developer Console](https://developer.adobe.com/console)
- [Firefly Services SDK](https://developer.adobe.com/firefly-services/docs/guides/sdks/)
- [PDF Services Node SDK](https://www.npmjs.com/package/@adobe/pdfservices-node-sdk)
- [App Builder Architecture](https://developer.adobe.com/app-builder/docs/guides/)
## Next Steps
For multi-environment setup, see `adobe-multi-env-setup`.Related Skills
workhuman-reference-architecture
Workhuman reference architecture for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman reference architecture".
wispr-reference-architecture
Wispr Flow reference architecture for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr reference architecture".
windsurf-reference-architecture
Implement Windsurf reference architecture with optimal project structure and AI configuration. Use when designing workspace configuration for Windsurf, setting up team standards, or establishing architecture patterns that maximize Cascade effectiveness. Trigger with phrases like "windsurf architecture", "windsurf project structure", "windsurf best practices", "windsurf team setup", "optimize for cascade".
windsurf-architecture-variants
Choose workspace architectures for different project scales in Windsurf. Use when deciding how to structure Windsurf workspaces for monorepos, multi-service setups, or polyglot codebases. Trigger with phrases like "windsurf workspace strategy", "windsurf monorepo", "windsurf project layout", "windsurf multi-service", "windsurf workspace size".
webflow-reference-architecture
Implement Webflow reference architecture — layered project structure, client wrapper, CMS sync service, webhook handlers, and caching layer for production integrations. Trigger with phrases like "webflow architecture", "webflow project structure", "how to organize webflow", "webflow integration design", "webflow best practices".
vercel-reference-architecture
Implement a Vercel reference architecture with layered project structure and best practices. Use when designing new Vercel projects, reviewing project structure, or establishing architecture standards for Vercel applications. Trigger with phrases like "vercel architecture", "vercel project structure", "vercel best practices layout", "how to organize vercel project".
vercel-architecture-variants
Choose and implement Vercel architecture blueprints for different scales and use cases. Use when designing new Vercel projects, choosing between static, serverless, and edge architectures, or planning how to structure a multi-project Vercel deployment. Trigger with phrases like "vercel architecture", "vercel blueprint", "how to structure vercel", "vercel monorepo", "vercel multi-project".
veeva-reference-architecture
Veeva Vault reference architecture for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva reference architecture".
vastai-reference-architecture
Implement Vast.ai reference architecture for GPU compute workflows. Use when designing ML training pipelines, structuring GPU orchestration, or establishing architecture patterns for Vast.ai applications. Trigger with phrases like "vastai architecture", "vastai design pattern", "vastai project structure", "vastai ml pipeline".
twinmind-reference-architecture
Production architecture for meeting AI systems using TwinMind: transcription pipeline, memory vault, action item workflow, and calendar integration. Use when implementing reference architecture, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind reference architecture", "twinmind reference architecture".
together-reference-architecture
Together AI reference architecture for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together reference architecture".
techsmith-reference-architecture
TechSmith reference architecture for Snagit COM API and Camtasia automation. Use when working with TechSmith screen capture and video editing automation. Trigger: "techsmith reference architecture".