System design
Design systems, services, and architectures.
Upstream publishes this file as a Claude skill (SKILL.md). Cursor reads the same SKILL.md shape. This page does not claim either product ships the file.
What the research says
Practitioner-backedThe requirements-first framework mirrors textbook practice. Clarifying ambiguous requirements before coding raised GPT-4 pass rates from 68.0% to 75.8% in one study, though that measured code generation, not design.
Checked Oct 17, 2026. How we rate evidence
Let your agent do it
Copy a prompt for Claude Code, Codex, or Cursor.
Paste it into your coding agent in this repo. It does the setup and asks before anything leaves your machine.
Runs the same job in your agent session, on the plan you are signed in with. No API key, no Action.
Install the "System design" agent skill from AgentFlows (https://agentflows.sh/skills/system-design) and use it with the plan I'm signed in with. No API key needed. Install these agent skills first. Download each SKILL.md from its source (respect its license) into .claude/skills/<name>/SKILL.md, or wherever this agent loads skills from: - System design: https://github.com/anthropics/knowledge-work-plugins/blob/main/engineering/skills/system-design/SKILL.md (Apache-2.0), notes at https://agentflows.sh/skills/system-design Then confirm the skill loaded, tell me in two lines when it kicks in, and offer to run it now on this repo.
The file
SKILL.md
Copy the upstream file, including its own frontmatter, into .claude/skills/system-design/SKILL.md.
.claude/skills/system-design/SKILL.md
--- name: system-design 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. --- # System Design Help design systems and evaluate architectural decisions. ## Framework ### 1. Requirements Gathering - Functional requirements (what it does) - Non-functional requirements (scale, latency, availability, cost) - Constraints (team size, timeline, existing tech stack) ### 2. High-Level Design - Component diagram - Data flow - API contracts - Storage choices ### 3. Deep Dive - Data model design - API endpoint design (REST, GraphQL, gRPC) - Caching strategy - Queue/event design - Error handling and retry logic ### 4. Scale and Reliability - Load estimation - Horizontal vs. vertical scaling - Failover and redundancy - Monitoring and alerting ### 5. Trade-off Analysis - Every decision has trade-offs. Make them explicit. - Consider: complexity, cost, team familiarity, time to market, maintainability ## 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.