software architecture planner
A rigorous 9-step framework to transform requirements into justified, production-ready software architectures.
$5
Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentssoftware architecture planner
Example session with this skill installed
Design a real-time inventory management system for a retail chain with 500 stores. Must handle peak holiday traffic, ensure eventual consistency across regions, and integrate with legacy ERP.
- Read your context and instructions
- Compiled the software architecture planner
- Generated the UI component
I have analyzed your inventory management requirements. I am recommending a
Modular Monolith with an Outbox Pattern for the MVP to manage complexity, evolving into a dedicated Event-Driven architecture as regional scaling demands increase.
Software Architecture: Retail Inventory Sync
1. Requirements Diagnosis
Scale: 500 stores, 20k SKU/store. Peak traffic: 5,000 writes/sec (checkout bursts). 2-year growth: 1,500 stores.
*
Constraints: Latency < 100ms for stock checks. PII compliance for customer orders. Legacy ERP sync (SOAP/XML) is the primary bottleneck.
- Failure Modes: ERP downtime, network partition between store and cloud, duplicate sale events during retry.
2. Architectural Tradeoff Matrix
| Option | Complexity | Scalability | Resilience | Cost | Risk |
|---|---|---|---|---|---|
| A: Modular Monolith | Low | Medium | Medium | Low | Low |
| B: Event-Driven (Kafka) | High | High | High | High | Medium |
| C: Serverless (Lambda) | Medium | High | Medium | Variable | Medium |
Recommendation: Option A. Given the team size and legacy ERP constraints, a modular monolith ensures ACID compliance for local inventory while using an outbox pattern for asynchronous ERP updates.
3. Component Definition: Inventory Core
- Responsibility: Authoritative stock count and reservation logic.
- Interfaces: REST API (POST /reserve, GET /availability).
- Data Storage: PostgreSQL 16 (Relational for transactional integrity).
- Dependencies: Must not call Payment Service directly; emits
StockReservedevent.
4. Data Architecture
erDiagram
STORE ||--o{ STOCK_LEVEL : contains
STOCK_LEVEL ||--o{ RESERVATION : tracks
PRODUCT ||--o{ STOCK_LEVEL : defines
Next steps
- Review the Risk Register regarding the legacy ERP integration latency.
- Validate the OpenAPI contract for the Inventory Core service.
- Initiate Phase 0 (PoC) for the store-to-cloud synchronization worker.
software-architecture-planner.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Vague requirements often lead to over-engineered distributed systems or brittle monoliths. Developers frequently jump to infrastructure choices like Kubernetes or Kafka before diagnosing actual scale needs and failure modes.
What it does
- Analyzes scale requirements to estimate throughput, data volume, and 5-year growth targets.
- Generates a comparative tradeoff matrix for three distinct architectural approaches (e.g., Modular Monolith vs. Event-Driven).
- Defines concrete component boundaries, interface contracts, and data ownership rules using DDD principles.
- Produces a phased implementation roadmap that prioritizes the critical path while flagging premature abstractions.
Frameworks & tools
Produces architectural artifacts including Mermaid diagrams, OpenAPI specs, JSON Schema, and OpenTelemetry observability strategies. Supports technology-specific recommendations for PostgreSQL, Redis, Kafka, AWS, and GCP.
Why this beats prompting it yourself
General prompts usually return high-level advice or generic microservices patterns. This skill enforces a 9-step rigorous diagnostic sequence that forces an audit of complexity and cost before a single line of code is written.
Use cases
- Transforming a raw product requirement document into a technical design doc.
- Performing a pre-implementation risk review to identify potential bottlenecks.
- Designing a migration path from a legacy monolith to a modern service architecture.
- Standardizing internal RFCs and system design proposals for engineering teams.
Known limitations
Requires specific input on expected user load or data volume to provide accurate scale estimates. Does not generate full application boilerplate code, only interface and contract definitions.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 19 days ago
- Passed all security checks, Safe to install