agent-development

Design and validate Claude Code plugin agent configurations and system prompts.

6|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/archibate/archibate-skills --skill agent-development-archibate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-development
Source: https://github.com/archibate/archibate-skills/tree/main/skills/agent-development
Command: npx skills add https://github.com/archibate/archibate-skills --skill agent-development-archibate

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Creating reliable, well-structured autonomous agents for Claude Code plugins is hard: authors must craft precise frontmatter, triggering examples, system prompts, and validate format and behavior to make agents discoverable, safe, and effective.

Core Features & Use Cases

  • Agent Templates: Ready-made frontmatter and system prompt patterns for common agent types (reviewers, test generators, docs, security).
  • Triggering Guidance: Concrete <example> blocks and commentary patterns to ensure agents activate in the right contexts and avoid false positives.
  • Validation & Tooling: Shell-based validation script and reference guides to check frontmatter fields, model/color/tools selection, system prompt structure, and example coverage.
  • Use Case: Create a code-review agent for a plugin, validate its frontmatter and examples, then test triggering scenarios before adding it to agents/ to ensure correct discovery and behavior.

Quick Start

Create an agent that reviews pull requests for security and code quality using the agent-creation template and validate it with the provided validation script.

Frequently Asked Questions about agent-development

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

FAQPage Schema
How do I create autonomous agents for Claude Code plugins?

To create autonomous agents for Claude Code plugins, design frontmatter, triggering examples, and system prompts using provided templates. This ensures agents are discoverable and correctly structured within plugin agents directories.

What is the best way to validate agent frontmatter and system prompts?

The best way to validate agent frontmatter and system prompts is running shell-based validation scripts that check field formats, model and tools selection, and example coverage to ensure correct agent discovery and behavior.

How do I configure agent triggering examples to avoid false positives in Claude Code?

Configuring agent triggering examples requires adding concrete example blocks and commentary patterns to ensure agents activate in the right contexts and avoid false positives during Claude Code plugin execution.

Does this provide templates for common agent types like code reviewers and test generators?

Yes, this provides ready-made frontmatter and system prompt templates for common agent types like code reviewers, test generators, docs, and security agents to accelerate Claude Code plugin development.

Can I test triggering scenarios for my agent before adding it to the agents directory?

Yes, you can test triggering scenarios before adding an agent to the agents directory by using the validation scripts and reference guides to verify example coverage and frontmatter fields.

Why does my Claude Code agent fail to activate in the correct context?

Claude Code agents fail to activate when triggering examples lack concrete blocks or commentary patterns, causing incorrect context matching. Validate example coverage and frontmatter to fix discovery issues.