Token导航 LogoToken导航

Agent Skill · 研究检索

multi-agent-dev-team(多 Agent 开发团队)

multi-agent-dev-team 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

multi-agent-dev-team 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 3,797。

总安装 39,552周安装 1,648GitHub Stars 公开资料未说明下载 13,184核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:multi-agent-dev-team(多 Agent 开发团队)
来源仓库:https://github.com/chloepark85/multi-agent-dev-team
安装命令:
openclaw skills install multi-agent-dev-team
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install multi-agent-dev-team

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

multi-agent-dev-team 实现 OpenClaw 中两个代理协作完成软件开发全流程。适合需求分析、编码实现与测试部署等环节的分工协作模式。通过 clawhub 安装后,Agent 可自动分派任务并合并输出结果。使用前需设定清晰的沟通协议与交付标准,保障协作质量。

注意版本控制与代码合并冲突处理,建议启用自动化 CI/CD 流程。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install multi-agent-dev-team;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

multi-agent-dev-team 怎么安装?

在终端执行 openclaw skills install multi-agent-dev-team。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

multi-agent-dev-team 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

multi-agent-dev-team 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

multi-agent-dev-team 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

multi-agent-dev-team 用的人多吗?

公开数据是累计安装 39,552 次,近一周安装 1,648 次,下载 13,184 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

multi-agent-dev-team 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
multi-agent-dev-team

多 Agent 开发团队 · 本页

39,552—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
Multi-Agent Dev Team
description
2-agent collaborative software development workflow for OpenClaw
homepage
https://ubik.systems
metadata
{"clawdbot":{"emoji":"🤝","requires":{"agents":["multi-agent-pm","multi-agent-dev"]}}}

Multi-Agent Dev Team

2-agent collaborative software development workflow for OpenClaw

Build complete software projects using AI agents that work together like a real development team.

What is this?

The Multi-Agent Dev Team skill provides a PM (Project Manager) and Dev (Developer) agent that collaborate to build software projects. You describe what you want, the PM breaks it down into tasks, and the Dev agent implements them.

Perfect for:

  • Landing pages and websites
  • Small web applications
  • Prototypes and MVPs
  • Code generation projects
  • Learning multi-agent workflows

Quick Start

1. Install the skill

npx clawhub install multi-agent-dev-team

2. Set up agents

The skill includes two pre-configured agents:

PM Agent (multi-agent-pm)

  • Handles project planning
  • Coordinates the Dev agent
  • Reports progress to you

Dev Agent (multi-agent-dev)

  • Implements code
  • Tests functionality
  • Commits to Git

3. Configure in ~/.openclaw/config.yaml

agents:
  multi-agent-pm:
    soul: ~/.openclaw/skills/multi-agent-dev-team/agents/pm-agent/SOUL.md
    model: anthropic/claude-sonnet-4-5-20250929  # or your preferred model
    
  multi-agent-dev:
    soul: ~/.openclaw/skills/multi-agent-dev-team/agents/dev-agent/SOUL.md
    model: google/gemini-2.5-flash  # faster for code generation

4. Start your PM agent

openclaw chat --agent multi-agent-pm

Usage Example

Building a Landing Page

You (Director):

Build me a Next.js landing page with hero section, features, and contact form. Use Tailwind CSS and TypeScript.

PM Agent:

I'll break this down into a clear task for the Dev agent. Starting now... *[Spawns Dev agent with detailed spec]* Dev agent is working on the project. I'll monitor progress and report back when complete.

PM Agent (later):

✅ Landing page completed! Deliverables: - Next.js 14+ App Router project - Hero, Features, Contact sections - Fully responsive design - TypeScript + Tailwind CSS - Git repository initialized Location: ~/projects/my-landing-page/ Ready for deployment. Would you like me to deploy to Vercel?

How It Works

Architecture

You (Director)
    ↓
PM Agent (Orchestrator)
    ↓
Dev Agent (Implementer)
    ↓
Working Code

Workflow

  1. You describe your project to the PM agent
  2. PM creates a structured task specification
  3. PM spawns Dev agent with the spec
  4. Dev implements the code
  5. PM reviews the deliverables
  6. PM reports completion (or requests revisions)
  7. Repeat steps 4-6 if needed (max 3 iterations)

Task Specification Format

The PM agent uses this template to communicate with Dev:

## Project: [NAME]
## Task: [ACTION]

## Requirements:
1. [Requirement 1]
2. [Requirement 2]

## Technical Constraints:
- [Constraint 1]
- [Constraint 2]

## Acceptance Criteria:
- [ ] [Criterion 1]
- [ ] [Criterion 2]

## Deliverables:
- [Deliverable 1]
- [Deliverable 2]

Supported Project Types

✅ Works Great

  • Next.js landing pages & apps
  • React components & SPAs
  • Node.js scripts & APIs
  • TypeScript projects
  • Static sites (HTML/CSS/JS)
  • Documentation sites

⚠️ Limited Support

  • Complex backend systems (use Pro version)
  • Real-time applications
  • Multi-service architectures
  • Mobile apps

❌ Not Recommended

  • Large enterprise systems
  • Mission-critical production code without human review
  • Projects requiring specialized agents (use Pro version)

Configuration Options

Agent Models

PM Agent (orchestration):

  • anthropic/claude-sonnet-4-5 - Best reasoning
  • google/gemini-2.5-flash - Fast & efficient
  • openai/gpt-4o - Balanced

Dev Agent (code generation):

  • google/gemini-2.5-flash - Fast iteration (recommended)
  • anthropic/claude-sonnet-4-5 - Higher quality
  • openai/gpt-4o-mini - Budget-friendly

Workspace Configuration

Set a dedicated workspace for projects:

agents:
  multi-agent-pm:
    soul: ~/.openclaw/skills/multi-agent-dev-team/agents/pm-agent/SOUL.md
    model: anthropic/claude-sonnet-4-5-20250929
    cwd: ~/dev-projects  # All projects created here

Best Practices

1. Start Small

Don't ask for everything at once. Start with an MVP:

❌ Bad:

Build a full e-commerce site with user auth, payments, admin dashboard, and inventory management.

✅ Good:

Build a simple product landing page with hero, features, and signup form.

2. Be Specific

The more specific your requirements, the better the result:

❌ Vague:

Make a nice website.

✅ Specific:

Create a Next.js landing page with: - Hero section with CTA button - 3-column feature grid - Contact form with email validation - Tailwind CSS styling - Dark mode support

3. Iterate Incrementally

Build in phases:

Phase 1: Basic structure Phase 2: Add features Phase 3: Polish & deploy

4. Review Output

Always review the generated code before deploying. The agents are good, but human oversight is important.

5. Provide Examples

If you have a specific style or pattern in mind, share examples:

Build a landing page similar to https://example.com, but for [your product].

Troubleshooting

"Dev agent didn't complete the task"

Check:

  1. Was the task specification clear?
  2. Are required tools available (Node.js, Git)?
  3. Did the agent hit resource limits?

Solution:

  • Simplify the task
  • Check PM agent logs via sessions_history
  • Try again with clearer requirements

"Code doesn't work"

Check:

  1. Dependencies installed? (npm install)
  2. Environment variables set?
  3. Correct Node.js version?

Solution:

  • Ask PM agent: "The code has errors. Please review and fix."
  • The PM will spawn Dev again for corrections

"Task took too long"

Solutions:

  • Break into smaller tasks
  • Use faster model for Dev agent (gemini-2.5-flash)
  • Simplify requirements

Examples

Example 1: Simple Landing Page

You: Build a landing page for a SaaS product called "TaskFlow". 
Include hero, features (3 cards), and pricing table. Use Next.js 
and Tailwind CSS.

PM: Working on it... 
[2 minutes later]
PM: ✅ TaskFlow landing page complete! Ready for deployment.

Example 2: React Component Library

You: Create a reusable Button component library with variants 
(primary, secondary, outline) and sizes (sm, md, lg). Use 
TypeScript and class-variance-authority.

PM: Task received. Spawning Dev agent...
[3 minutes later]
PM: ✅ Button component library complete with Storybook examples.

Example 3: API Integration

You: Build a Next.js app that fetches and displays GitHub user 
profiles. Include search functionality and responsive cards.

PM: Starting development...
[4 minutes later]
PM: ✅ GitHub profile viewer complete with search and error handling.

Upgrading to Pro

Want more power? Upgrade to Multi-Agent Dev Team Pro ($49):

Pro Features

  • 🎯 6 specialized agents: PM, Architect, Dev, QA, DevOps, BizDev
  • 🔄 Lobster pipelines: Automated workflows with approval gates
  • 🏗️ Architecture design: Dedicated agent for system design
  • ✅ Automated QA: Code review & testing agent
  • 🚀 DevOps automation: Deployment & CI/CD setup
  • 💼 Business planning: Market research & strategy agent
  • 📚 Comprehensive guides: English + Korean setup docs

Get Pro →

Support

License

MIT License - See LICENSE file for details

Credits

Built by UBIK Collective

Powered by OpenClaw


Ready to build with AI agents? Install now:

npx clawhub install multi-agent-dev-team

平台分布

OpenClaw

81.05%
按下载量换算10,686

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills