Crewai Multi Agent
技能 已验证 活跃Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
To empower developers to build autonomous AI agents that collaborate effectively on complex tasks, enabling sophisticated multi-agent systems and production workflows.
功能
- Multi-agent orchestration framework
- Role-based agent collaboration with memory
- Sequential/hierarchical task execution
- Standalone, no LangChain dependencies
- Support for custom tools and YAML configuration
- Event-driven flows for complex workflows
使用场景
- Building teams of specialized AI agents
- Enabling autonomous collaboration between agents
- Implementing role-based task delegation (e.g., researcher, writer)
- Creating production workflows requiring memory and observability
非目标
- General-purpose LLM app development (use LangChain)
- Complex stateful workflows with cycles (use LangGraph)
- Acting as a replacement for individual LLM providers
安装
请先添加 Marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skills质量评分
已验证类似扩展
Agentic Jujutsu
99Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Stream Chain
99Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
Agent Multi Repo Swarm
98Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm
Parallel Feature Development
98Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system simultaneously, when establishing file ownership to prevent merge conflicts in a shared codebase, when designing interface contracts so parallel implementers can build against each other's APIs before they are ready, or when deciding whether to use vertical slices versus horizontal layers for a full-stack feature.
Init
100创建或优化存储库的 AGENTS.md 文件，提供最少、高信号的说明，涵盖代理无法从代码库推断的不可发现的编码约定、工具怪癖、工作流偏好和项目特定规则。在为新存储库设置代理说明或 Claude 配置时，当现有的 AGENTS.md 文件过长、通用或过时，当代理反复犯可避免的错误，或当存储库工作流发生变化且需要修剪代理配置时使用。应用可发现性过滤器—省略 Claude 可从 README、代码、配置或目录结构中学到的任何内容—并应用质量门，以验证每行是否仍然准确且具有操作意义。
Trader Regime
100Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy