agent-development

Create Claude Code agent markdown files with YAML frontmatter and second-person system prompts.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/moughamir/justwaitit-review --skill agent-development-moughamir
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-development
Source: https://github.com/moughamir/justwaitit-review/tree/main/.agents/skills/agent-development
Command: npx skills add https://github.com/moughamir/justwaitit-review --skill agent-development-moughamir

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you design, configure, and document Claude Code agents so they reliably trigger for the right requests and follow a robust system-prompt workflow.

Core Features & Use Cases

  • Agent file format guidance: Defines how to structure an agent as a markdown file with YAML frontmatter plus a system-prompt body.
  • Triggerable agent descriptions: Shows how to write descriptions with concrete triggering conditions and multiple example blocks so the right agent activates.
  • Operational configuration support: Covers required fields like name, description, model, color, and optional tool restrictions via least-privilege.
  • System prompt engineering: Provides a template for responsibilities, process steps, quality standards, output format, and edge-case handling.

Quick Start

Use the agent-development skill to generate a Claude Code agent markdown file by writing a YAML frontmatter with name, description (including 2-4 examples), model set to inherit, and an appropriate color, then add a second-person system prompt that specifies responsibilities, process, output format, and edge cases.

Frequently Asked Questions about agent-development

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

FAQPage Schema
How do I create a Claude Code agent with YAML frontmatter and a system prompt?

Trigger conditions for Claude Code agents are configured by writing descriptions with concrete activation scenarios and 2-4 example blocks, ensuring the agent reliably initiates for the correct requests across plugin workflows.

What is the correct structure for a Claude Code agent markdown file?

A Claude Code agent markdown file requires YAML frontmatter for operational configuration like name, model, and color, paired with a second-person system prompt template defining responsibilities, quality standards, and output format.

How do I restrict tools for a Claude Code agent using least-privilege?

You restrict tools for a Claude Code agent by applying least-privilege configuration in the YAML frontmatter, ensuring the autonomous agent only accesses the specific tools required for its designated workflow tasks.

How do I configure trigger conditions for a Claude Code agent?

Trigger conditions for Claude Code agents are configured by writing descriptions with concrete activation scenarios and 2-4 example blocks, ensuring the agent reliably initiates for the correct requests across plugin workflows.

How do I write a system prompt for an autonomous Claude Code agent?

Writing a system prompt for an autonomous agent involves using a second-person perspective to define responsibilities, process steps, quality standards, output format, and edge-case handling for reliable activation.