Agent Skills › evolution-foundation/evo-nexus › dev-team

dev-team

GitHub

按需并行启动多个工程代理以处理大型上下文任务，适用于多文件重构、代码审计等可拆分为独立流的工作。

.claude/skills/dev-team/SKILL.md evolution-foundation/evo-nexus

Trigger Scenarios

多模块大文件重构跨子系统性能调查大规模代码库审计

Install

npx skills add evolution-foundation/evo-nexus --skill dev-team -g -y

More Options

Non-standard path

npx skills add https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/dev-team -g -y

Use without installing

npx skills use evolution-foundation/evo-nexus@dev-team

指定 Agent (Claude Code)

npx skills add evolution-foundation/evo-nexus --skill dev-team -a claude-code -g -y

安装 repo 全部 skill

npx skills add evolution-foundation/evo-nexus --all -g -y

预览 repo 内 skill

npx skills add evolution-foundation/evo-nexus --list

SKILL.md

Frontmatter

{
    "name": "dev-team",
    "description": "On-demand spawning of multiple engineering agents in parallel for large-context work. Use when a task is too big for a single agent and the work can be split into independent streams."
}

Dev Team

Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.

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

Use When

Multi-file refactor across 10+ files in different modules
Codebase audit that benefits from parallel exploration
Performance investigation across multiple subsystems
Documentation pass across many files

Do Not Use When

Sequential dependencies (B needs A's output)
Single-file change
Task fits within a single agent's context

Workflow

Decompose the task into N independent streams
Assign each stream to the most appropriate agent (apex / bolt / lens / etc.)
Spawn agents in parallel via Task tool
Collect results as they return
Synthesize into a unified output
Save to workspace/development/research/[C]team-{topic}-{date}.md

Streams Example

For "audit the entire auth module":

Stream 1: @scout-explorer → map all auth files
Stream 2: @vault-security → security audit
Stream 3: @lens-reviewer → code quality review
Stream 4: @grid-tester → test coverage analysis
Stream 5: @apex-architect → architecture analysis

All spawn in parallel, results combine into one report.

Output

## Team Investigation — {topic}

### Streams
1. {stream 1 result summary}
2. {stream 2 result summary}
...

### Cross-stream Findings
[Insights that emerged from combining results]

### Recommendation
[Unified next step]