Skill

agent-development-pack

Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.

Install

npx claudepluginhub organvm-iv-taxis/a-i--skills --plugin document-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

A curated bundle for building, testing, and coordinating AI agent systems with proper handoff and tool integration.

SKILL.md

Similar Skills

agent-eval

Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.

everything-claude-code

157.7k

agent-harness-construction

Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.

everything-claude-code

157.7k

accessibility

Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.

everything-claude-code

157.7k

Stats

Stars6

Forks3

Last CommitMar 20, 2026

Actions

View Source View Plugin View on GitHub View README

Agent Development Pack

A curated bundle for building, testing, and coordinating AI agent systems with proper handoff and tool integration.

What's Included

agent-swarm-orchestrator — Design multi-agent systems with coordinated swarms and task distribution

agent-testing-patterns — Test agent tool use, non-deterministic outputs, and multi-turn conversations

cross-agent-handoff — Transfer context between agent sessions with structured handoff protocols

mcp-builder — Build MCP (Model Context Protocol) servers for extending agent capabilities

prompt-engineering-patterns — Design effective prompts with structured formats and chain-of-thought

Getting Started

Install this bundle when building AI agent systems. The recommended workflow:

Design: Use prompt-engineering-patterns to architect system prompts and tool definitions

Build: Use mcp-builder for custom tool servers and agent-swarm-orchestrator for multi-agent coordination

Test: Use agent-testing-patterns for unit, integration, and E2E agent testing

Coordinate: Use cross-agent-handoff for reliable session continuity

This pack is the foundation for ORGAN-IV (orchestration) agent development.