Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
dralgorhythm avatar

Designing Systems

  • 74 installs
  • 111 repo stars
  • Updated July 24, 2026
  • dralgorhythm/claude-agentic-framework

Guides Claude Code through system-design decisions - architecture, boundaries, data flow, and trade-offs - so a solo builder ships a coherent design before writing code.

About

A Claude Code skill that walks an AI agent through designing software systems - defining architecture, component boundaries, data flow, and the key trade-offs behind each decision. A solo builder reaches for it when starting a non-trivial feature or service and wants a coherent architecture on paper before implementation begins.

  • Structured system-design workflow for agents
  • Covers architecture boundaries and trade-offs
  • Part of a full agentic engineering framework

Designing Systems by the numbers

  • 74 all-time installs (skills.sh)
  • Ranked #5,508 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/dralgorhythm/claude-agentic-framework --skill designing-systems

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs74
repo stars111
Last updatedJuly 24, 2026
Repositorydralgorhythm/claude-agentic-framework

What it does

Guides Claude Code through system-design decisions - architecture, boundaries, data flow, and trade-offs - so a solo builder ships a coherent design before writing code.

Who is it for?

Planning the architecture of a new feature or service before coding

Skip if: Small one-off scripts that need no design

Files

SKILL.mdMarkdownGitHub ↗

Designing Systems

Workflows

  • [ ] Requirements: Gather functional and non-functional requirements
  • [ ] Diagrams: Create C4 diagrams (Context, Container)
  • [ ] Data: Define data model and storage strategy
  • [ ] API: Define interfaces and contracts
  • [ ] Risks: Identify single points of failure
  • [ ] Document: Save to ./artifacts/adr_[topic].md

Feedback Loops

1. Draft design document 2. Review with stakeholders 3. Create POC for risky components 4. Refine design based on POC 5. Finalize ADR

Blueprint Template

Every system design should include:

1. High-Level Diagram: Mermaid graph showing components 2. Component Boundaries: Clear responsibility definitions 3. API Definitions: OpenAPI or GraphQL specs 4. Data Models: Schema definitions 5. Trade-off Analysis: Rationale for key decisions

C4 Model Levels

Level 1: Context

Who uses the system? What external systems does it interact with?

Level 2: Container

What are the major deployable units? (APIs, databases, queues)

Level 3: Component

What are the major building blocks within each container?

Level 4: Code

Class/function level (usually not needed in architecture docs)

Trade-off Analysis

For major decisions, explicitly document:

DecisionOption AOption B
Pros......
Cons......
When to Choose......

Non-Functional Requirements

Always consider:

  • Scalability: Expected load, growth rate
  • Availability: SLA targets, failure modes
  • Latency: P50, P95, P99 requirements
  • Security: Authentication, authorization, data protection
  • Cost: Infrastructure, operational overhead

Resources

  • System Design Template
  • ADR Template

Related skills

AI & Agent Buildingbackendintegrations

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.