Ai Agents Architect

This one's for when you need Claude to design autonomous AI systems that won't quietly fail on you. It covers the full stack: ReAct and Plan-and-Execute loops, tool registries, hierarchical memory, multi-agent orchestration with supervisor patterns. The sharp edges section is genuinely useful, calling out iteration limits (critical), vague tool descriptions, and the classic mistake of throwing 20+ tools at an agent. The philosophy is pragmatic: agents should fail loudly, multi-agent adds overhead you need to justify, and memory is for context not a crutch. Good if you're building anything beyond basic function calling and want to avoid the common traps.

Install to Claude Code

npx -y skills add sickn33/antigravity-awesome-skills --skill ai-agents-architect --agent claude-code