Agent Development

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

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/ace8991/agentos --skill agent-development-ace8991
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Agent Development
Source: https://github.com/ace8991/agentos/tree/main/.tmp_claude_code/claude-code-main/plugins/plugin-dev/skills/agent-development
Command: npx skills add https://github.com/ace8991/agentos --skill agent-development-ace8991

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Writing Claude Code plugin agents requires precise YAML frontmatter, well-structured system prompts, and triggering examples, and mistakes in any of these cause agents to fail to load or trigger incorrectly. ## 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 Design: Supplies proven templates for analysis, generation, validation, and orchestration agents with process steps, quality standards, and edge-case handling. - Triggering Examples: Documents the <example> block format so agents trigger reliably on explicit, implicit, and proactive user requests. - Use Case: You want to add a code review agent to your plugin. Use this Skill to generate the agent file with proper frontmatter, a structured system prompt, and triggering examples, then validate it with the included script. ## Quick Start Create a Claude Code agent that reviews code for quality and security issues and validate the resulting agent file.

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 second-person system prompt. The description must include triggering conditions and 2-4 example blocks showing when the agent activates.

What frontmatter fields are required for a Claude Code agent?

Four fields are required: name (lowercase with hyphens, 3-50 characters), description (triggering conditions with example blocks), 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, a user message, an assistant response, and commentary explaining why the agent triggers. Include 2-4 examples covering explicit requests, implicit needs, and proactive triggering after relevant work.

Why is my Claude Code agent not triggering?

Agents fail to trigger when description examples lack relevant keywords, contexts do not match actual usage, or commentary does not explain the triggering logic. Add more examples with varied user phrasings and verify the assistant invokes the agent in each example.

How long should an agent system prompt be?

System prompts should be between 20 and 10000 characters, with 500-3000 characters being typical. Include clear responsibilities, step-by-step process, quality standards, output format, and edge-case handling written in second person.