Agent Development

Create and validate Claude Code plugin agents with frontmatter, system prompts, and triggering examples.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Clay-HHK/claude-skills --skill agent-development-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Agent Development
Source: https://github.com/Clay-HHK/claude-skills/tree/main/agent-identifier
Command: npx skills add https://github.com/Clay-HHK/claude-skills --skill agent-development-clay-hhk

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, well-crafted triggering descriptions, and structured system prompts, and mistakes in any of these cause agents to fail to trigger or behave unpredictably. ## Core Features & Use Cases - Agent File Authoring: Provides the complete agent markdown format covering name, description, model, color, and tools frontmatter fields with validation rules. - System Prompt Patterns: Supplies proven templates for analysis, generation, validation, and orchestration agents with responsibilities, process steps, and output formats. - Triggering Examples: Documents the example block format with context, user message, and commentary so agents trigger reliably on the right requests. - Use Case: When building a plugin that needs a code review agent, use this Skill to generate the agent file with proper triggering examples, then validate it with the included validation script. ## Quick Start Ask the AI to create a Claude Code agent that reviews pull requests, including frontmatter, triggering examples, and a structured system prompt.

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 with example blocks showing when the agent activates.

What frontmatter fields are required for Claude Code agents?▼

Agents require name, description, model, and color fields. The name must be 3-50 lowercase characters with hyphens, model accepts inherit, sonnet, opus, or haiku, and color accepts blue, cyan, green, yellow, magenta, or red. The tools field is optional.

How do I make an agent trigger reliably in Claude Code?▼

Write a description starting with triggering conditions and include 2-4 example blocks. Each example needs context, the user message, the assistant response, and commentary explaining why the agent triggers. Cover both explicit requests and proactive scenarios.

Can I restrict which tools an agent can access?▼

Yes, add a tools array to the frontmatter listing allowed tool names like Read, Write, Grep, or Bash. If omitted, the agent has access to all tools. Limiting tools follows the principle of least privilege for read-only analysis agents.

Why is my agent not triggering on user requests?▼

Triggering fails when description examples lack relevant keywords, context does not match actual usage, or commentary does not explain the triggering logic. Add more examples covering different phrasings of the same intent and validate with the included script.