# System Architect

> >

- **Type:** Skill
- **Install:** `agentstack add skill-batterfried-philosophy172-agent-startup-skills-system-architect`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [batterfried-philosophy172](https://agentstack.voostack.com/s/batterfried-philosophy172)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [batterfried-philosophy172](https://github.com/batterfried-philosophy172)
- **Source:** https://github.com/batterfried-philosophy172/Agent-Startup-Skills/tree/main/skills/system-architect

## Install

```sh
agentstack add skill-batterfried-philosophy172-agent-startup-skills-system-architect
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# System Architect — Design Agent

## Purpose

Design a complete, justified system architecture before any code is written.
Prevent "spaghetti architecture" by making deliberate, documented choices.

## When to Use

- After MVP scope is approved
- When choosing a tech stack for a new project
- When designing API contracts or system structure

## Process

### Step 1: Tech Stack Selection
For each layer, recommend a technology with a one-line justification:

| Layer | Choice | Why |
|---|---|---|
| Frontend | e.g., Next.js | SSR for SEO, React ecosystem |
| Backend | e.g., Next.js API Routes | Unified codebase, serverless-ready |
| Database | e.g., PostgreSQL | Relational data, free tier on Supabase |
| Auth | e.g., NextAuth.js | Free, supports OAuth providers |
| Hosting | e.g., Vercel | Free tier, zero-config deploys |

**Constraint:** Prefer free-tier-friendly technologies unless the user specifies a budget.

### Step 2: System Architecture
Describe the architecture in plain text or a mermaid diagram:
- How do the frontend, backend, and database connect?
- What is the request flow for the core user action?
- Where does authentication happen?

### Step 3: Project File Structure
Present the complete folder/file tree:
```
project-root/
├── src/
│   ├── app/           # Pages and routes
│   ├── components/    # Reusable UI components
│   ├── lib/           # Business logic and utilities
│   ├── api/           # API route handlers
│   └── db/            # Database schema and migrations
├── tests/             # Test files
├── public/            # Static assets
├── .env.example       # Environment variable template
├── package.json
└── README.md
```

### Step 4: API Endpoint Inventory
List every API endpoint the MVP needs:

| Method | Endpoint | Description | Auth Required |
|---|---|---|---|
| POST | /api/auth/register | Create new user | No |
| POST | /api/auth/login | Authenticate user | No |
| GET | /api/[resource] | List resources | Yes |

### Step 5: External Services
List any third-party services required:
- What it does, why it's needed, what it costs, and the free tier limits

### Output
Produce an `architecture.md` file with all sections above.

## Exit Criteria
- Every tech choice has a documented justification
- File structure is complete (no "etc." or "...")
- All API endpoints are listed with methods and auth requirements
- External service costs are identified

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [batterfried-philosophy172](https://github.com/batterfried-philosophy172)
- **Source:** [batterfried-philosophy172/Agent-Startup-Skills](https://github.com/batterfried-philosophy172/Agent-Startup-Skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-batterfried-philosophy172-agent-startup-skills-system-architect
- Seller: https://agentstack.voostack.com/s/batterfried-philosophy172
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.