team-builder

Organize agent personas into parallel teams for task execution.

Updated Apr 4, 2026
One-click install
npx skills add https://github.com/mitul-bhatia/Vibes --skill team-builder-mitul-bhatia
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-builder
Source: https://github.com/mitul-bhatia/Vibes/tree/main/.github/skills/team-builder
Command: npx skills add https://github.com/mitul-bhatia/Vibes --skill team-builder-mitul-bhatia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browse and assemble agent personas into coordinated, parallel teams to accelerate cross-domain work.

Core Features & Use Cases

  • Interactive domain-aware selection: browse agents within subdirectories or by filename prefixes.
  • Ad-hoc team assembly: compose cross-domain teams (e.g., Security Engineer + SEO Specialist) for a task.
  • Parallel execution and synthesis: spawn selected agents in parallel and aggregate results for quick decisions.

Quick Start

Open the Team Builder, select up to five agents from available domains, and provide a task description to run them in parallel.

Frequently Asked Questions about team-builder

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

FAQPage Schema
How do I assemble cross-domain agent personas into a parallel team for task execution?

You assemble cross-domain agent personas into a parallel team by browsing an agents directory, selecting up to five agents, and running them concurrently with your task description to aggregate outputs for synthesis.

How does parallel processing work for multiple agent personas during workflow orchestration?

Parallel processing for multiple agent personas works by parsing agent markdown files to derive identities, spawning selected agents concurrently, and aggregating their parallel outputs for final cross-domain synthesis.

Can I select agents from specific subdirectories for multi-domain collaboration?

Yes, you can select agents for multi-domain collaboration by browsing available agents within specific subdirectories or filtering them by filename prefixes to build ad-hoc cross-domain teams.

What is the maximum number of agents I can spawn in parallel for a single task?

The maximum number of agents you can spawn in parallel for a single task is five, allowing you to balance scalable task assignment across diverse agents without overwhelming the workflow orchestration.

Do I need markdown files to define agent identities before team assembly?

Yes, you need markdown files to define agent identities because the team assembly mechanism parses these agent markdown documents to derive personas before spawning them for parallel execution.