Agent Design

Use when the user asks about building agents, designing tool sets for LLMs, structuring agent workflows, reviewing existing agent architectures, creating action spaces, coordinating subagents, or evaluating agent behavior. Also trigger when you see terms like "agent harness", "tool calling design", "action space", "agent loop", "progressive disclosure", "subagent", "elicitation", or when the user asks how to make an LLM interact with external tools effectively. Applies to Claude API agents primarily, but principles are model-agnostic. Do NOT use for generating AGENTS.md files — use the AgentsMD skill instead.

fauzanazz Updated 0 repo stars

File contents

fauzanazz/claude-skills commit 425cd86f83

Frequently asked questions

npx get-skill add fauzanazz/agent-design