create-agent

Define and enforce standardized Claude Code agent authoring guidelines.

10|1|Updated Mar 2, 2026
One-click install
npx skills add https://github.com/yagizdo/quiver --skill create-agent-yagizdo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-agent
Source: https://github.com/yagizdo/quiver/tree/main/skills/create-agent
Command: npx skills add https://github.com/yagizdo/quiver --skill create-agent-yagizdo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a structured template and field requirements to standardize the creation of Claude Code agents, reducing ambiguity and enabling consistent behavior across projects.

Core Features & Use Cases

  • Standard templates for agent files with mandatory YAML frontmatter
  • Clear guidance on required fields, role/personalization, and methodology sections
  • Reusable patterns for debugging, testing, and ongoing maintenance across projects

Quick Start

Create a new agent file using the template structure and frontmatter rules described in this guide.

Frequently Asked Questions about create-agent

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

FAQPage Schema
How do I create a Claude Code agent file with the correct YAML frontmatter structure?

Claude Code agent authoring guidelines require mandatory YAML frontmatter fields including name, description, and model. Standardized templates enforce this structure, reducing ambiguity and ensuring consistent agent behavior across different projects.

What sections are required when authoring a Claude Code agent?

Authoring a Claude Code agent requires prescribed body sections including examples, role/persona, methodology, and output format. Quality checks and toxicity safeguards are also enforced to ensure reliable and reusable agent behavior.

What is the best way to standardize Claude Code agent templates across multiple projects?

Standardizing Claude Code agent templates across projects requires enforcing strict frontmatter validation and prescribed body sections. This approach guarantees reliable behavior, reusability, and consistent quality checks for every agent file.

Does this agent authoring template include safeguards for content toxicity?

Yes, the agent authoring template includes toxicity safeguards as part of its quality checks. This ensures generated Claude Code agents adhere to safety guidelines and maintain reliable, standardized behavior across projects.

Why do I need frontmatter validation for Claude Code agents?

Frontmatter validation for Claude Code agents ensures required fields like name, description, and model are present and correct. This standardization reduces ambiguity and enables consistent agent behavior across projects.

Can I reuse Claude Code agent patterns for debugging and testing?

Yes, Claude Code agent patterns are reusable for debugging and testing. The authoring guidelines provide reusable templates and methodologies designed for ongoing maintenance and reliable behavior across projects.