Agent Development

Create and validate Claude Code agent files with frontmatter, system prompts, and triggering examples.

1|Updated May 10, 2026
One-click install
npx skills add https://github.com/Tgoldi/claude-skills --skill agent-development-tgoldi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Agent Development
Source: https://github.com/Tgoldi/claude-skills/tree/main/agent-development
Command: npx skills add https://github.com/Tgoldi/claude-skills --skill agent-development-tgoldi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Writing Claude Code agents requires precise frontmatter fields, well-structured system prompts, and triggering examples, 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 Example Guidance: Documents the <example> block format with context, user message, and commentary so agents trigger reliably. - 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 pull requests for 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 a Claude Code agent file?

Create a markdown file in your plugin's agents/ directory with YAML frontmatter containing name, description, model, and color fields, followed by a system prompt written in second person. Include 2-4 <example> blocks in the description showing when the agent should trigger.

What frontmatter fields are required for Claude Code agents?

Agents require name (lowercase with hyphens, 3-50 characters), description (triggering conditions with examples), 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 (the situation), user (the exact request), assistant (the response), and <commentary> explaining why the agent triggers. Include both explicit requests and proactive triggering scenarios with varied phrasings.

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 covering different phrasings of the same intent.

How long should an agent system prompt be?

System prompts should be between 20 and 10,000 characters, with 500-3,000 characters being typical. Include clear responsibilities, step-by-step process, quality standards, output format, and edge case handling written in second person.