If you're building autonomous agents for Claude Code plugins, this walks you through the complete structure: YAML frontmatter with name, description, model, color, and tools, plus the system prompt that defines behavior. The description field is critical since it determines when Claude triggers your agent, so you get specific guidance on writing triggering conditions with prose examples. Includes validation rules (identifiers must be 3-50 chars, lowercase with hyphens), best practices for system prompts (second person, step-by-step processes, quality standards), and the distinction between agents (autonomous multi-step work) versus commands (user-initiated actions). Useful whether you're writing agents manually or using AI-assisted generation.
npx skills add https://github.com/anthropics/claude-plugins-official --skill agent-development