agent-development

Create and validate Claude Code plugin subagent definitions with frontmatter and system prompts.

2|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/hamzaPixl/pixl-ai --skill agent-development-hamzapixl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-development
Source: https://github.com/hamzaPixl/pixl-ai/tree/main/packages/crew/skills/agent-development
Command: npx skills add https://github.com/hamzaPixl/pixl-ai --skill agent-development-hamzapixl

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides a practical workflow and templates for creating, documenting, and validating Claude Code plugin agents so teams can produce reliable autonomous subagents with consistent frontmatter, triggering examples, and system prompts.

Core Features & Use Cases

  • Agent templates and examples: Ready-made frontmatter patterns and example blocks to define when an agent should trigger and how it should behave.
  • System prompt design guidance: Structured patterns and checklists to write clear second-person system prompts with responsibilities, processes, output formats, and edge cases.
  • Validation and testing: A validation script and reference checks to ensure required frontmatter fields, example blocks, model/color settings, and prompt length/structure meet project rules.
  • Use Case: Rapidly author a new code-review or test-generation agent with correct triggering examples and validate it before adding to a Claude Code plugin.

Quick Start

Ask the agent-development skill to draft a new agent frontmatter, include two triggering examples and a concise system prompt for the requested role.

Frequently Asked Questions about agent-development

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

FAQPage Schema
How do I create subagents for Claude Code plugins?

To create subagents for Claude Code plugins, you draft YAML frontmatter, define triggering examples, and structure a system prompt to specify agent behavior and tool access restrictions.

How do I validate Claude Code agent frontmatter and system prompts?

You validate Claude Code agent frontmatter by running a validation script that checks for required fields, example presence, model and color settings, and system prompt structure against project rules.

What is the best way to design triggering scenarios for plugin agents?

The best way to design triggering scenarios for plugin agents is to include proactive and reactive example blocks within the frontmatter to define exactly when the agent should activate.

How do I write a system prompt for an autonomous subagent?

You write a system prompt for an autonomous subagent using structured patterns and checklists to define responsibilities, processes, output formats, and edge cases in clear second-person language.

Do I need to define tool access restrictions when authoring Claude Code subagents?

Yes, you need to define tool access restrictions when authoring Claude Code subagents to ensure the autonomous agent operates safely within its designated scope and responsibilities.

Why does my Claude Code agent fail validation checks?

Your Claude Code agent fails validation checks when required frontmatter fields are missing, example blocks are absent, or the system prompt does not meet length and structure quality requirements.