القائمة
Design multi-agent AI systems — agent architectures, tool use, memory systems,
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Consult and write the ARAYA postoffice — the operational-directive channel. Advisory, never a gate: read it at cycle start, append your entry at cycle end, consider its directives, never be blocked by it. Governance acts never travel the postoffice.
Audit and enforce brand compliance across all projects and platforms — logo,
Design REST and GraphQL APIs following OpenAPI 3.1 standards. Produce complete
Connect frontend to backend — type-safe API clients, request/response handling,
Implement authentication and authorization middleware — JWT validation, role-based
Design scalable component architectures — design systems, component libraries,
| name | agent-design |
| description | Design multi-agent AI systems — agent architectures, tool use, memory systems, |
Design multi-agent AI systems — agent architectures, tool use, memory systems, inter-agent communication, and safety guardrails — building autonomous agents that plan, act, and learn within defined boundaries.
Single-prompt LLM interactions are limited; agents that can reason, use tools, and iterate solve complex multi-step problems. This skill designs agent architectures with clear roles, tools, memory, and safety constraints.
When building autonomous agents. When a single LLM call is insufficient for the task (multi-step reasoning, external tool use, iterative refinement). When designing ARAYA-like multi-agent systems.
Task domain, required capabilities, constraints, safety requirements.
An agent architecture specification with roles, tools, memory model, and safety guardrails — ready for implementation.
