Agent Development

Create and validate autonomous agent configurations for Claude Code plugins.

1|1|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/voxxov222/Claude-code- --skill agent-development-voxxov222
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Agent Development
Source: https://github.com/voxxov222/Claude-code-/tree/main/temp-repo/plugins/plugin-dev/skills/agent-development
Command: npx skills add https://github.com/voxxov222/Claude-code- --skill agent-development-voxxov222

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Building autonomous agents for Claude Code plugins requires precise frontmatter fields, triggering examples, and structured system prompts, and mistakes in any of these cause agents to trigger incorrectly or behave unpredictably. ## Core Features & Use Cases - Agent File Authoring: Provides the complete markdown format with YAML frontmatter covering name, description, model, color, and tools fields, plus naming and length validation rules. - Triggering Example Design: Documents the <example> block format with context, user message, assistant response, and commentary so agents activate on the right requests. - System Prompt Patterns: Supplies templates for analysis, generation, validation, and orchestration agents with responsibilities, process steps, quality standards, and output formats. - Use Case: When you need a code review agent for your plugin, follow the templates to write agents/code-reviewer.md with proper triggering examples, then run scripts/validate-agent.sh to confirm the structure passes all checks. ## Quick Start Ask the AI to create a code review agent for a Claude Code plugin using this skill's format and validation rules.

Frequently Asked Questions about Agent Development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an agent for a Claude Code plugin?

Create a markdown file in the plugin's agents/ directory with YAML frontmatter containing name, description, model, and color fields, followed by a system prompt body. The description must include triggering conditions and 2-4 example blocks showing when the agent activates.

What fields are required in agent frontmatter?

Agent frontmatter requires name (lowercase with hyphens, 3-50 characters), description (triggering conditions with examples), model (inherit, sonnet, opus, or haiku), and color (blue, cyan, green, yellow, magenta, or red). The tools field is optional and restricts tool access.

How do I write triggering examples for an agent description?

Use example blocks containing Context (the situation), user (the exact request), assistant (the response), and commentary (why the agent triggers). Include 2-4 examples covering explicit requests, proactive triggering, and varied phrasings of the same intent.

How do I validate an agent file structure?

Run scripts/validate-agent.sh with the agent file path to check frontmatter structure, required fields, name format and length, model and color values, and system prompt presence. The script reports errors for missing fields and warnings for style issues.

What are the limits for agent names and system prompts?

Agent names must be 3-50 characters using lowercase letters, numbers, and hyphens, starting and ending with alphanumeric characters. System prompts should be 20-10,000 characters, with 500-3,000 characters recommended for clarity.