arch-system
Domain: arch · Model class: strong
Description
Section titled “Description”Use this skill when the user wants to work on Designing AI-native systems with agent layers, memory, retrieval, safety, and observability. Triggers include “design an AI-native system”, “architect my agent platform”, “how do I structure my AI application”. Do NOT use when review existing code quality (use code-analysis-quality).
Purpose
Section titled “Purpose”Designing AI-native systems with agent layers, memory, retrieval, safety, and observability. This skill provides structured guidance, references, and worked examples to help produce high-quality, actionable outputs.
Trigger Phrases
Section titled “Trigger Phrases”- “design an AI-native system”
- “architect my agent platform”
- “how do I structure my AI application”
- “system architecture for AI”
Anti-Triggers
Section titled “Anti-Triggers”- review existing code quality (use code-analysis-quality)
- debug a runtime issue (use core-debugging-assistant)
Intake Questions
Section titled “Intake Questions”- What is the user’s goal and current state?
- What constraints (time, team, compliance) apply?
- Are there existing artifacts (specs, code, benchmarks) to reference?
Output Contract
Section titled “Output Contract”- architecture recommendation
- tradeoff summary
- system component framing
- risk and next-step guidance