Ai Agents Architect

This is your guide when you're building AI agents that need to do things on their own without going off the rails. It covers the core patterns like ReAct loops and plan-and-execute architectures, plus practical stuff like tool registries and memory management. The sharp edges table is the real value here: it calls out common failure modes like agent loops without iteration limits and tool overload that will bite you in production. Good fit if you're moving past basic LLM calls into agents that chain actions together, especially multi-agent systems where coordination matters.

Install to Claude Code

npx -y skills add davila7/claude-code-templates --skill ai-agents-architect --agent claude-code