What model should I use for my Claude Code agent?

It is generally recommended to use 'inherit' so the agent utilizes the same model as the parent process. However, you can specify 'sonnet', 'opus', or 'haiku' if the task requires specific capabilities or cost profiles.

What is a Claude Code Agent?

Agents are autonomous subprocesses within Claude Code plugins designed to handle complex, multi-step tasks independently using specific tools and structured system prompts.

What are the naming rules for agent identifiers?

Agent names must be between 3 and 50 characters, use only lowercase letters, numbers, and hyphens, and must start and end with an alphanumeric character.

How do I trigger a specific agent in Claude Code?

Agents are triggered based on the 'description' field in their frontmatter. This field must include specific triggering conditions and multiple XML-formatted examples showing user requests and expected assistant responses.

Claude Code Agent Development

Name: Claude Code Agent Development
Author: nsalvacao

bynsalvacao

0•

开发者工具

Provides comprehensive guidance and best practices for building autonomous agents within the Claude Code plugin ecosystem.

This skill serves as a definitive resource for developers looking to create production-grade autonomous agents for Claude Code. It offers structured templates and validation rules for agent frontmatter, including name, color, and tool configuration, while emphasizing the critical role of triggering conditions and system prompt design. By following these established patterns, developers can build agents that handle complex, multi-step tasks independently with predictable behavior and efficient tool usage.

主要功能

01Standardized YAML frontmatter templates for agent metadata

02AI-assisted agent generation patterns for rapid plugin development

03Best practices for structured system prompt design using second-person perspective

04Validation rules for agent identifiers, colors, and tool permissions

050 GitHub stars

06Strategic guidance for writing effective triggering conditions with examples

使用场景

01Designing a new autonomous agent for a specific coding or analysis workflow

02Optimizing agent triggering conditions to ensure reliable and proactive invocation

03Structuring complex system prompts for reliable multi-step task execution

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nsalvacao/nsalvacao-claude-code-plugins agent-development

For use in Claude.ai and ChatGPT

主要功能

01Standardized YAML frontmatter templates for agent metadata

02AI-assisted agent generation patterns for rapid plugin development

03Best practices for structured system prompt design using second-person perspective

04Validation rules for agent identifiers, colors, and tool permissions

050 GitHub stars

06Strategic guidance for writing effective triggering conditions with examples

使用场景

01Designing a new autonomous agent for a specific coding or analysis workflow

02Optimizing agent triggering conditions to ensure reliable and proactive invocation

03Structuring complex system prompts for reliable multi-step task execution

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nsalvacao/nsalvacao-claude-code-plugins agent-development

For use in Claude.ai and ChatGPT