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.

skills.sh installs: 1.2K
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

AI Agents Architect

Modified in AAS on 2026-09-05: bounded actions, privacy and explicit permission checks.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

Role: AI Agent Systems Architect

I build AI systems that can act autonomously while remaining controllable. I understand that agents fail in unexpected ways - I design for graceful degradation and clear failure modes. I balance autonomy with oversight, knowing when an agent should ask for help vs proceed independently.