dev-team

Spawn multiple engineering agents in parallel for large-context tasks.

520|175|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/EvolutionAPI/evo-nexus --skill dev-team-evolutionapi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-team
Source: https://github.com/EvolutionAPI/evo-nexus/tree/main/.claude/skills/dev-team
Command: npx skills add https://github.com/EvolutionAPI/evo-nexus --skill dev-team-evolutionapi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

On-demand spawning of multiple engineering agents to tackle large-context work. When a task is too big for a single agent and the work can be split into independent streams, spin up multiple engineering agents working in parallel.

Core Features & Use Cases

  • Parallel team spawning: create multiple agents to explore different subsystems concurrently.
  • Structured workflow: follows a defined sequence from decompose to synthesis and saves output to workspace.
  • Use Case: ideal for multi-file refactors across modules, comprehensive codebase audits, performance investigations, and large documentation passes.

Quick Start

Decompose the task into independent streams, assign streams to appropriate agents, spawn parallel teams, collect results, synthesize, and save to the designated workspace path.

Frequently Asked Questions about dev-team

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

FAQPage Schema
How do I run parallel code audits across multiple modules?

Parallel code audits across modules require spawning multiple engineering agents concurrently to explore different subsystems, collect results, and synthesize a unified output saved to your workspace.

What is the best way to handle multi-file refactors that exceed a single agent's capacity?

Multi-file refactors exceeding a single agent are handled by decomposing the task into independent streams, assigning them to parallel spawned agents, and synthesizing the unified output into your workspace.

How do I decompose a large architecture review into independent streams for parallel agents?

Decomposing a large architecture review requires splitting the task into independent streams, assigning streams to appropriate agents, spawning parallel teams via the Task tool, and synthesizing the collected results.

Can I spawn parallel engineering teams for large documentation passes?

Spawning parallel engineering teams for large documentation passes is fully supported by assigning independent streams to multiple agents and synthesizing their collected results into a unified workspace output.

When should I not use parallel engineering agents for a software engineering task?

Parallel engineering agents should not be used when a task cannot be split into independent streams or when the work is small enough for a single agent to handle without task decomposition.