Engineering ArchitectureDesignSystems

Senior Architect

System architecture design, dependency analysis, and technical decisions.

Install for

Real Conversations

See how the Senior Architect skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

Redesigning our Rails monolith handling ~5,000 orders/day. Checkout takes 8-12 seconds. Looking at event-driven microservices. Where do I start?

Agent

Architecture: Strangler Fig + Async Checkout Core

Don't rip out the monolith — strangle it. Extract the slowest path (checkout) first.

Why checkout is 8-12s (almost certainly): Synchronous chain: inventory check → Stripe charge → send email → send SMS. Each waits for the previous. Event-driven breaks the chain after payment.

Target architecture:

Checkout API (Go/Node) → Kafka: orders.created
                           ├→ Inventory Service  (reserve stock)
                           ├→ Fulfillment Service (pick/pack)
                           └→ Notification Service (email + SMS)

Rails monolith: catalog, user mgmt, admin — untouched in Phase 1

Phase 1 (Month 1-2) — fix latency:

Thin checkout API: validates cart, charges Stripe, publishes order.created event
Email/SMS move to async Kafka consumers
Checkout response time: 8-12s → <800ms

Phase 2 (Month 3-4) — inventory + fulfillment:

Saga pattern for distributed transaction: reserve → charge → fulfill
Compensating transactions: release reservation if charge fails

Kafka topic sizing for 5k orders/day:

Topic	Partitions	Retention
orders.created	6	7 days
orders.failed	3	30 days

Rule: Add a new service only when a bounded context needs different scaling OR separate team ownership. Two services in Month 1 is enough.

You

15-engineer team, 4 frontend apps, 3 shared component libraries, 2 Python services, 1 mobile app. Polyrepo now and dependency management is chaos. Should we switch?

Agent

Decision: Monorepo with Turborepo

Version drift in shared libraries and coordinated cross-repo PRs are the canonical monorepo problems. At 15 engineers you'll get full benefit without enterprise-scale pain.

Why Turborepo over Nx:

Simpler config for JS/Python mixed stack (Nx's Python support is awkward)
Remote caching via Vercel (free under 10GB/month)
Incremental adoption — you don't rewrite CI in one shot

Proposed workspace structure:

/apps
  web-marketing/   # Next.js
  web-app/         # Next.js
  web-admin/       # React
  mobile/          # React Native
/packages
  ui/              # shared component library
  design-tokens/   # Tailwind config, color palette
  api-client/      # generated OpenAPI types + fetch wrappers
/services
  api/             # Python FastAPI (isolated venv)
  workers/         # Python Celery (isolated venv)

Migration — don't big-bang it:

Week 1: scaffold monorepo, import one frontend app, configure Turborepo cache
Week 2-3: migrate the shared UI library — highest-value step, unblocks everything else
Week 4+: migrate apps one at a time

Risks to plan for:

Git history: use git filter-repo to preserve it — do not squash on import
CI time: configure Turborepo remote cache before migrating or CI will slow down temporarily
Python: keep independent virtualenvs per service — don't force a shared Python toolchain

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4.8 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models support 100K+ context.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Senior Architect?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

Install for

← Browse all skills