skills.rest
samymity
samymityCOMMUNITY
Explore all skills by this author →
GitHub

team-builder

Select multiple agent personas and dispatch them in parallel to synthesize a unified response.

1|Updated Mar 3, 2026
Search Tags:#parallel execution#agent selection#team composition#task dispatch#persona prompts#multi-agent synthesis#dynamic discovery
One-click install
npx skills add https://github.com/samymity/bridge-ventures-backend --skill team-builder-samymity
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: team-builder
Source: https://github.com/samymity/bridge-ventures-backend/tree/main/.claude/skills/team-builder
Command: npx skills add https://github.com/samymity/bridge-ventures-backend --skill team-builder-samymity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Team-builder helps you quickly choose the right set of agent personas from many available markdown agent files and run them in parallel on the same task, then deliver a unified result.

Core Features & Use Cases

  • Interactive agent discovery & browsing: Automatically probes local and global agent markdown directories, extracts agent names and summaries, and groups them by inferred domains.
  • Ad-hoc parallel team composition: Lets you select one or more domains or specific agent names, with an enforced maximum of 5 agents to keep outputs focused and efficient.
  • Parallel agent execution with synthesis: Spawns all selected agents independently, captures failures inline, and—when multiple agents run—produces a synthesis that highlights agreements, tensions, and next steps.
  • Use cases: Use it to compose cross-functional teams such as Security + SEO + Architecture for a launch review, or to gather complementary findings for a complex product, technical, or go-to-market decision.

Quick Start

Use team-builder to browse available agent domains and select up to five agents, then describe the task you want them to work on.

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 on the same task?▼

To run multiple agents in parallel, you select up to five agent personas and dispatch them simultaneously; the system captures each output independently and generates a unified synthesis highlighting agreements and tensions.

What is parallel multi-agent synthesis and when do I need it?▼

Parallel multi-agent synthesis is the process of spawning multiple independent agents on one task and merging their outputs. You need it for complex decisions requiring cross-functional review, such as combining Security, SEO, and Architecture perspectives.

How do I discover and select agent markdown files across project directories?▼

Agent discovery happens automatically by probing local and global directories for markdown files with YAML-defined metadata. The system groups found agents by inferred domains, allowing you to select specific names or entire domains dynamically.

Can I dispatch more than five agents at the same time?▼

No, a strict max-five enforcement limits parallel agent dispatch to five personas. This constraint keeps outputs focused and efficient, preventing unmanageable synthesis results when running multiple agents simultaneously.

What's the best way to compose a cross-functional team for a launch review?▼

The best way to compose a cross-functional team is to select complementary agent domains like Security and Architecture. The system dispatches them in parallel and synthesizes grouped outputs to deliver a unified review result.

Does team-builder work with flat directory layouts for agent files?▼

Yes, dynamic discovery supports both flat and subdirectory layouts for agent markdown files. It probes project-local and global directories, grouping agents by inferred domains regardless of the file structure.

Related Skills

Explore More Software Engineering Skills→
RambleRainbowRambleRainbow

team-builder

Selects AI agent personas and dispatches them in parallel for complex tasks.

Community
Advanced
himanshu231204himanshu231204
2

team-builder

Automate selection, parallel dispatch, and result synthesis of multiple AI agents.

Community
Intermediate
SufficientDaikonSufficientDaikon
8

dispatching-parallel-agents

Dispatch multiple independent agents in parallel to address distinct subsystem tasks.

Community
Intermediate
bakwankawabakwankawa

dispatching-parallel-agents

Dispatch parallel agents to investigate independent problems concurrently.

Community
Basic