メニュー
System architecture skill for designing scalable, maintainable software systems. Covers microservices/monolith decisions, API design, DB selection, caching, security, and scalability planning.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/georgekhananaev/claude-skills-vault --skill system-architectコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Shapes how every reply to the user gets written - plain everyday words instead of corporate or AI-sounding phrasing, real sentences instead of bullet-heavy formatting, no forced dash punctuation, and at most a rare bit of dry humor when it genuinely fits. Use this for every conversational response written to the user in this project, not only on special request - check it before replying, the same way a person reads over their own message before hitting send.
Safety-first Firebase CLI (firebase-tools v15) skill for full project control — deploy, Hosting (sites/channels/rollback), Cloud Functions (+secrets), Firestore (databases/indexes/backups/delete), Realtime Database, Auth import/export, Remote Config, App Distribution, App Hosting, Extensions, Data Connect, Emulator Suite & MCP server. Classifies every command by risk tier via a deterministic classifier script and gates destructive/irreversible/cost-incurring ops behind AskUserQuestion confirmation; enforces the --non-interactive/--force contract so nothing hangs and nothing is auto-confirmed. Wrong-project preflight prevents deploying to prod by accident. Ships a 3-level self-test (static classifier battery, live read-only, guarded live-write w/ cleanup). Use when running, planning, or debugging any `firebase` command.
Run OpenAI Codex CLI for coding tasks, implementation, reviews, and second-opinion audits with mandatory task-based routing across GPT-5.6-or-newer models. Use when a user asks to run, ask, or use Codex; says "codex prompt"; wants a Codex code/logic/plan audit; or wants Claude to delegate work to OpenAI models. Inspect the live Codex model catalog, explicitly pin an eligible model and reasoning effort on every invocation, route clear high-volume work to Luna, everyday work to Terra, and difficult or high-value work to Sol. Use Sol with max reasoning for plan audits. Never invoke or fall back to GPT-5.5, GPT-5.4, GPT-5.3-Codex-Spark, OSS, or any model older than GPT-5.6.
| name | system-architect |
| description | System architecture skill for designing scalable, maintainable software systems. Covers microservices/monolith decisions, API design, DB selection, caching, security, and scalability planning. |
Design scalable, maintainable software systems.
/architect, /design, /system-design1. Functional: Core features, workflows, integrations
2. Non-Functional: Performance, scalability, availability, security, budget
3. Constraints: Tech stack, team expertise, timeline, existing systems
Reference patterns.json for patterns, tech recommendations, trade-offs.
# Architecture Design Document
## 1. Overview
[High-level description]
## 2. Goals & Non-Goals
## 3. Architecture
### System Diagram
### Components
| Component | Responsibility | Technology |
|-----------|---------------|------------|
### Data Flow
## 4. Technical Decisions
### Decision 1: [Title]
- Context | Options | Decision | Rationale
## 5. API Design
## 6. Data Model
## 7. Security
## 8. Scalability
## 9. Monitoring & Observability
## 10. Risks & Mitigations
| Pattern | Use When | Trade-offs |
|---|---|---|
| Sync REST | Simple CRUD | Tight coupling |
| Async Queue | Decoupling | Complexity |
| Event Sourcing | Audit trail | Storage |
| CQRS | Read/write opt | Eventual consistency |
| GraphQL | Flexible queries | Caching |
| gRPC | High perf | Browser support |
| Pattern | Use When | Trade-offs |
|---|---|---|
| SQL | ACID, complex queries | Scaling |
| NoSQL | Flexibility, scale | Consistency |
| Cache-aside | Read-heavy | Invalidation |
| Pattern | Purpose |
|---|---|
| Circuit Breaker | Prevent cascade failures |
| Retry w/ Backoff | Handle transient failures |
| Bulkhead | Isolate failures |
| Timeout | Prevent hanging |
| Fallback | Graceful degradation |
Reference structures.json for:
Frontend: React/Next.js, Vue/Nuxt, Angular
Backend: Node.js, Go, Python (FastAPI), Rust
DB: PostgreSQL, MongoDB
Cache: Redis | Queue: RabbitMQ, SQS, Kafka
Search: Elasticsearch, Meilisearch
WebSocket: Socket.io, ws
Pub/Sub: Redis, Kafka
Processing: Spark, Flink
Storage: S3, GCS
Warehouse: Snowflake, BigQuery
Pipeline: Airflow, Dagster
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Client │────▶│ API Gateway │────▶│ Services │
└─────────────┘ └─────────────┘ └─────────────┘
│ │
▼ ▼
┌─────────────┐ ┌─────────────┐
│ Auth │ │ Database │
└─────────────┘ └─────────────┘
sequenceDiagram
Client->>API: Request
API->>Auth: Validate Token
Auth-->>API: Valid
API->>Service: Process
Service->>DB: Query
DB-->>Service: Data
Service-->>API: Response
API-->>Client: Response
| Criterion | Weight | Description |
|---|---|---|
| Scalability | High | Can it handle growth? |
| Maintainability | High | Easy to modify/debug? |
| Performance | Med-High | Meets latency/throughput? |
| Cost | Medium | Infra + dev cost |
| Security | High | Meets requirements? |
| Complexity | Medium | Team can build/operate? |
**Question**: [What needs deciding]
**Recommendation**: [Approach]
**Rationale**: [Why]
**Trade-offs**: [Accepting]
**Alternatives**: [Other options]