Skill Tracer
Skills › Knowledge Work Plugins › system-design

system-design

skill · 42 lines · Apache-2.0 · engineering/skills/system-design/SKILL.md

The facts

Its description

Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.

The description the agent reads to decide when to use it.

From its settingsline 3

When it starts

The agent picks this skill when someone asks how to design or architect a system, service, or API — questions about architecture choices, data modeling, or where service boundaries should fall. It is a design-and-trade-offs conversation, not a coding or debugging one.

Things a person might say (the model's guesses)

  • “How should we architect the notifications service so it survives 10x growth?”
  • “Design a system for syncing inventory between our warehouse and the storefront.”
  • “What's the right architecture for our API — REST, GraphQL, or gRPC?”

A model's summary of when it is used.

A model's reading

What leads to it

Other skills that hand off to this one, call it, require it or offer it instead, as a model read them.

A model's reading

Licence

Apache-2.0, from LICENSE

The terms its author shares it under, which let it be shown here.

From the repositorylicence text

The text

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1---
2name: system-design
3description: Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.
4---
5
6# System Design
7
8Help design systems and evaluate architectural decisions.
9

System Design

Help design systems and evaluate architectural decisions.

Raw lines 1 to 9
Names a skill architecture :8
10## Framework

Framework

Raw lines 10 to 11
12### 1. Requirements Gathering
13- Functional requirements (what it does)
14- Non-functional requirements (scale, latency, availability, cost)
15- Constraints (team size, timeline, existing tech stack)

1. Requirements Gathering

  • Functional requirements (what it does)
  • Non-functional requirements (scale, latency, availability, cost)
  • Constraints (team size, timeline, existing tech stack)
Raw lines 12 to 16
17### 2. High-Level Design
18- Component diagram
19- Data flow
20- API contracts
21- Storage choices

2. High-Level Design

  • Component diagram
  • Data flow
  • API contracts
  • Storage choices
Raw lines 17 to 22
23### 3. Deep Dive
24- Data model design
25- API endpoint design (REST, GraphQL, gRPC)
26- Caching strategy
27- Queue/event design
28- Error handling and retry logic

3. Deep Dive

  • Data model design
  • API endpoint design (REST, GraphQL, gRPC)
  • Caching strategy
  • Queue/event design
  • Error handling and retry logic
Raw lines 23 to 29
30### 4. Scale and Reliability
31- Load estimation
32- Horizontal vs. vertical scaling
33- Failover and redundancy
34- Monitoring and alerting

4. Scale and Reliability

  • Load estimation
  • Horizontal vs. vertical scaling
  • Failover and redundancy
  • Monitoring and alerting
Raw lines 30 to 35
36### 5. Trade-off Analysis
37- Every decision has trade-offs. Make them explicit.
38- Consider: complexity, cost, team familiarity, time to market, maintainability

5. Trade-off Analysis

  • Every decision has trade-offs. Make them explicit.
  • Consider: complexity, cost, team familiarity, time to market, maintainability
Raw lines 36 to 39
40## Output
42Produce clear, structured design documents with diagrams (ASCII or described), explicit assumptions, and trade-off analysis. Always identify what you'd revisit as the system grows.

Output

Produce clear, structured design documents with diagrams (ASCII or described), explicit assumptions, and trade-off analysis. Always identify what you'd revisit as the system grows.

Raw lines 40 to 42

From anthropics/knowledge-work-plugins at 2574e29, 2026-10-27. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.