agent-development

Transform user requirements into YAML frontmatter, system prompts, and triggering examples for agent files.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/onelee85/my-skills --skill agent-development-onelee85
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-development
Source: https://github.com/onelee85/my-skills/tree/main/claude-plugins-official/plugins/plugin-dev/skills/agent-development
Command: npx skills add https://github.com/onelee85/my-skills --skill agent-development-onelee85

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Agent Development Skill provides a structured approach to transforming user needs into robust, self-contained agent configurations for Claude Code plugins. It ensures consistent metadata, system prompts, and triggering examples so plugins can deploy autonomous agents with minimal additional guidance.

Core Features & Use Cases

  • Frontmatter discipline: mandatory fields (name, description, model, color) and optional fields (tools, version) to standardize agent metadata across plugins.
  • System prompt design: guidance to craft explicit responsibilities, processing steps, edge cases, output formats, and quality standards.
  • Triggering examples: best practices for 2-4 examples showing explicit and proactive usage across scenarios such as code changes, documentation requests, tests generation, and security reviews.
  • Validation & testing: recommended validation scripts and workflows to verify agent structure and trigger behavior before deployment.

Quick Start

Draft a complete agent file by composing frontmatter, a robust system prompt, and 2-4 triggering examples, then save it as agents/[identifier].md.

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 autonomous agent for a Claude Code plugin?

To create an autonomous agent for a Claude Code plugin, draft a configuration file containing YAML frontmatter, a system prompt, and triggering examples, then save it under the agents directory as a markdown file.

What is a Claude Code agent configuration file?

A Claude Code agent configuration file is a self-contained markdown document that standardizes agent metadata, system prompts, and triggering examples to deploy autonomous agents within plugins.

How do I write a system prompt for a plugin agent?

Write a system prompt for a plugin agent by explicitly defining its responsibilities, processing steps, edge cases, output formats, and quality standards to ensure robust autonomous execution.

What fields are required in agent frontmatter for Claude Code?

Required fields in agent frontmatter for Claude Code include name, description, model, and color, while optional fields like tools and version help standardize agent metadata across plugins.

How many triggering examples should an autonomous agent include?

An autonomous agent should include 2 to 4 triggering examples that demonstrate explicit and proactive usage across scenarios like code changes, documentation requests, and security reviews.

How do I validate a Claude Code agent before deployment?

Validate a Claude Code agent before deployment by running recommended validation scripts and workflows to verify the agent file structure and trigger behavior within the plugin environment.