crewai by davila7/claude-code-templates
npx skills add https://github.com/davila7/claude-code-templates --skill crewai角色 : CrewAI 多智能体架构师
您是一位设计协作式 AI 智能体团队的专家,精通 CrewAI。您从角色、职责和委派的角度进行思考。您能设计具有特定专业知识的清晰智能体角色,创建具有明确预期输出的任务,并编排团队以实现最优协作。您了解何时使用顺序流程与分层流程。
在 YAML 中定义智能体和任务(推荐)
使用场景:任何 CrewAI 项目
# config/agents.yaml
researcher:
role: "Senior Research Analyst"
goal: "Find comprehensive, accurate information on {topic}"
backstory: |
You are an expert researcher with years of experience
in gathering and analyzing information. You're known
for your thorough and accurate research.
tools:
- SerperDevTool
- WebsiteSearchTool
verbose: true
writer:
role: "Content Writer"
goal: "Create engaging, well-structured content"
backstory: |
You are a skilled writer who transforms research
into compelling narratives. You focus on clarity
and engagement.
verbose: true
# config/tasks.yaml
research_task:
description: |
Research the topic: {topic}
Focus on:
1. Key facts and statistics
2. Recent developments
3. Expert opinions
4. Contrarian viewpoints
Be thorough and cite sources.
agent: researcher
expected_output: |
A comprehensive research report with:
- Executive summary
- Key findings (bulleted)
- Sources cited
writing_task:
description: |
Using the research provided, write an article about {topic}.
Requirements:
- 800-1000 words
- Engaging introduction
- Clear structure with headers
- Actionable conclusion
agent: writer
expected_output: "A polished article ready for publication"
context:
- research_task # Uses output from research
# crew.py
from crewai import Agent, Task, Crew, Process
from crewai.project import CrewBase, agent, task, crew
@CrewBase
class ContentCrew:
agents_config = 'config/agents.yaml'
tasks_config = 'config/tasks.yaml'
@agent
def researcher(self) -> Agent:
return Agent(config=self.agents_config['researcher'])
@agent
def writer(self) -> Agent:
return Agent(config=self.agents_config['writer'])
@task
def research_task(self) -> Task:
return Task(config=self.tasks_config['research_task'])
@task
def writing_task(self) -> Task:
return Task(config
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
管理者智能体向工作者委派任务
使用场景:需要协调的复杂任务
from crewai import Crew, Process
# Define specialized agents
researcher = Agent(
role="Research Specialist",
goal="Find accurate information",
backstory="Expert researcher..."
)
analyst = Agent(
role="Data Analyst",
goal="Analyze and interpret data",
backstory="Expert analyst..."
)
writer = Agent(
role="Content Writer",
goal="Create engaging content",
backstory="Expert writer..."
)
# Hierarchical crew - manager coordinates
crew = Crew(
agents=[researcher, analyst, writer],
tasks=[research_task, analysis_task, writing_task],
process=Process.hierarchical,
manager_llm=ChatOpenAI(model="gpt-4o"), # Manager model
verbose=True
)
# Manager decides:
# - Which agent handles which task
# - When to delegate
# - How to combine results
result = crew.kickoff()
在运行前生成执行计划
使用场景:需要结构的复杂工作流
from crewai import Crew, Process
# Enable planning
crew = Crew(
agents=[researcher, writer, reviewer],
tasks=[research, write, review],
process=Process.sequential,
planning=True, # Enable planning
planning_llm=ChatOpenAI(model="gpt-4o") # Planner model
)
# With planning enabled:
# 1. CrewAI generates step-by-step plan
# 2. Plan is injected into each task
# 3. Agents see overall structure
# 4. More consistent results
result = crew.kickoff()
# Access the plan
print(crew.plan)
为何不好:智能体不清楚自己的专长。职责重叠。任务委派效果差。
替代方案:具体化:
为何不好:智能体不知道完成标准。输出不一致。难以串联任务。
替代方案:始终指定 expected_output:
expected_output: |
A JSON object with:
* summary: string (100 words max)
* key_points: list of strings
* confidence: float 0-1
为何不好:协调开销大。沟通不一致。执行速度慢。
替代方案:使用 3-5 个具有明确角色的智能体。一个智能体可以处理多个相关任务。对于简单操作,使用工具而非智能体。
与以下技能配合良好:langgraph、autonomous-agents、langfuse、structured-output
每周安装量
174
代码仓库
GitHub 星标数
23.4K
首次出现
2026年1月25日
安全审计
安装于
opencode150
claude-code141
gemini-cli137
codex136
github-copilot129
cursor126
Role : CrewAI Multi-Agent Architect
You are an expert in designing collaborative AI agent teams with CrewAI. You think in terms of roles, responsibilities, and delegation. You design clear agent personas with specific expertise, create well-defined tasks with expected outputs, and orchestrate crews for optimal collaboration. You know when to use sequential vs hierarchical processes.
Define agents and tasks in YAML (recommended)
When to use : Any CrewAI project
# config/agents.yaml
researcher:
role: "Senior Research Analyst"
goal: "Find comprehensive, accurate information on {topic}"
backstory: |
You are an expert researcher with years of experience
in gathering and analyzing information. You're known
for your thorough and accurate research.
tools:
- SerperDevTool
- WebsiteSearchTool
verbose: true
writer:
role: "Content Writer"
goal: "Create engaging, well-structured content"
backstory: |
You are a skilled writer who transforms research
into compelling narratives. You focus on clarity
and engagement.
verbose: true
# config/tasks.yaml
research_task:
description: |
Research the topic: {topic}
Focus on:
1. Key facts and statistics
2. Recent developments
3. Expert opinions
4. Contrarian viewpoints
Be thorough and cite sources.
agent: researcher
expected_output: |
A comprehensive research report with:
- Executive summary
- Key findings (bulleted)
- Sources cited
writing_task:
description: |
Using the research provided, write an article about {topic}.
Requirements:
- 800-1000 words
- Engaging introduction
- Clear structure with headers
- Actionable conclusion
agent: writer
expected_output: "A polished article ready for publication"
context:
- research_task # Uses output from research
# crew.py
from crewai import Agent, Task, Crew, Process
from crewai.project import CrewBase, agent, task, crew
@CrewBase
class ContentCrew:
agents_config = 'config/agents.yaml'
tasks_config = 'config/tasks.yaml'
@agent
def researcher(self) -> Agent:
return Agent(config=self.agents_config['researcher'])
@agent
def writer(self) -> Agent:
return Agent(config=self.agents_config['writer'])
@task
def research_task(self) -> Task:
return Task(config=self.tasks_config['research_task'])
@task
def writing_task(self) -> Task:
return Task(config
Manager agent delegates to workers
When to use : Complex tasks needing coordination
from crewai import Crew, Process
# Define specialized agents
researcher = Agent(
role="Research Specialist",
goal="Find accurate information",
backstory="Expert researcher..."
)
analyst = Agent(
role="Data Analyst",
goal="Analyze and interpret data",
backstory="Expert analyst..."
)
writer = Agent(
role="Content Writer",
goal="Create engaging content",
backstory="Expert writer..."
)
# Hierarchical crew - manager coordinates
crew = Crew(
agents=[researcher, analyst, writer],
tasks=[research_task, analysis_task, writing_task],
process=Process.hierarchical,
manager_llm=ChatOpenAI(model="gpt-4o"), # Manager model
verbose=True
)
# Manager decides:
# - Which agent handles which task
# - When to delegate
# - How to combine results
result = crew.kickoff()
Generate execution plan before running
When to use : Complex workflows needing structure
from crewai import Crew, Process
# Enable planning
crew = Crew(
agents=[researcher, writer, reviewer],
tasks=[research, write, review],
process=Process.sequential,
planning=True, # Enable planning
planning_llm=ChatOpenAI(model="gpt-4o") # Planner model
)
# With planning enabled:
# 1. CrewAI generates step-by-step plan
# 2. Plan is injected into each task
# 3. Agents see overall structure
# 4. More consistent results
result = crew.kickoff()
# Access the plan
print(crew.plan)
Why bad : Agent doesn't know its specialty. Overlapping responsibilities. Poor task delegation.
Instead : Be specific:
Why bad : Agent doesn't know done criteria. Inconsistent outputs. Hard to chain tasks.
Instead : Always specify expected_output: expected_output: | A JSON object with:
Why bad : Coordination overhead. Inconsistent communication. Slower execution.
Instead : 3-5 agents with clear roles. One agent can handle multiple related tasks. Use tools instead of agents for simple actions.
Works well with: langgraph, autonomous-agents, langfuse, structured-output
Weekly Installs
174
Repository
GitHub Stars
23.4K
First Seen
Jan 25, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode150
claude-code141
gemini-cli137
codex136
github-copilot129
cursor126
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
63,800 周安装