team-builder

Discover and dispatch specialized AI agent teams in parallel for cross-functional evaluation.

Updated May 9, 2026
One-click install
npx skills add https://github.com/kk20300113-png/my-claude-skills --skill team-builder-kk20300113-png
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-builder
Source: https://github.com/kk20300113-png/my-claude-skills/tree/main/team-builder
Command: npx skills add https://github.com/kk20300113-png/my-claude-skills --skill team-builder-kk20300113-png

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually coordinating multiple specialized AI agents for complex, multi-faceted tasks is time-consuming and prone to oversight, as it requires running each agent individually and manually consolidating results from different perspectives.

Core Features & Use Cases

  • Dynamic Agent Discovery: Automatically finds available agent personas from local project or global directories, supporting both flat and subdirectory file layouts with no hardcoded agent lists.
  • Flexible Team Selection: Lets you pick agents by domain, name, or number, with a built-in 5-agent limit to avoid excessive token usage and diminishing returns.
  • Parallel Dispatch & Synthesis: Runs all selected agents simultaneously and compiles their outputs into a unified report highlighting agreements, conflicts, and recommended next steps.
  • Use Case: Need to evaluate a new product feature from security, SEO, and architecture angles? Select those three specialized agents in one step to get a cross-functional review without running each workflow separately.

Quick Start

Use the team-builder skill to select the security engineer, SEO specialist, and software architect agents to review your upcoming product launch for cross-functional risks and gaps.

Frequently Asked Questions about team-builder

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

FAQPage Schema
How do I run multiple AI agents in parallel for cross-functional evaluation?

Run multiple AI agents in parallel by dynamically discovering specialized personas and dispatching them simultaneously. This eliminates manual coordination by synthesizing each agent's output into a unified report highlighting consensus, conflicts, and next steps.

What is dynamic agent discovery and how does it work for multi-agent workflows?

Dynamic agent discovery automatically finds available agent personas from local project or global directories, supporting both flat and subdirectory file layouts. It avoids hardcoded agent lists, allowing flexible team selection by domain, name, or number for complex tasks.

Can I evaluate a single project feature from security, SEO, and architecture angles at the same time?

Yes, you can evaluate a single project from security, SEO, and architecture angles simultaneously. Select specialized cross-functional agents in one step to get a unified review without running each workflow separately, synthesizing parallel outputs into one report.

Is there a limit to how many agents I can assign to one parallel dispatch task?

There is a 5-agent maximum per team for parallel dispatch. This limit optimizes token usage and prevents diminishing returns, ensuring your multi-agent workflow remains efficient while synthesizing cross-functional outputs into a unified report.

How do I manually consolidate outputs when coordinating multiple specialized AI agents?

You no longer need to manually consolidate outputs from multiple specialized AI agents. Parallel dispatch and synthesis automatically compiles diverse expert domain inputs into a unified report, highlighting agreements, conflicts, and recommended next steps.

Why does my multi-agent workflow use excessive tokens when reviewing complex tasks?

Multi-agent workflows use excessive tokens when dispatching too many agents without limits. Enforcing a 5-agent maximum per team optimizes token usage and prevents diminishing returns during cross-functional evaluation and parallel output synthesis.