Menü
Workflow patterns and gotchas for CrewAI. Directs to RAG for implementation.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
This skill should be used when the user asks about "visual builder", "no-code agent builder", "drag and drop", "ThinkingConfig", "extended thinking", "chain of thought", "reasoning", or needs guidance on using ADK's visual development tools or configuring advanced reasoning capabilities.
This skill should be used when the user asks about "callbacks", "lifecycle hooks", "before_model_call", "after_tool_call", "plugins", "session state", "state management", "artifacts", "file uploads", "events", "EventActions", "human-in-the-loop", "confirmation", "memory", "MemoryService", "long-term memory", "remember across sessions", "RAG", "retrieval augmented generation", "grounding", "knowledge base", "vector search", or needs guidance on customizing agent behavior, intercepting execution, managing state across turns, implementing approval workflows, or implementing persistent memory or grounding agent responses in external knowledge.
This skill should be used when the user asks about "creating a new ADK project", "initializing ADK", "setting up Google ADK", "adk create command", "ADK project structure", "YAML agent configuration", "creating an agent", "LlmAgent", "BaseAgent", "custom agent", "agent with different model", "Claude with ADK", "OpenAI with ADK", "LiteLLM", "multi-model agent", or needs guidance on bootstrapping an ADK development environment, authentication setup, choosing between Python code and YAML-based agent definitions, agent configuration, model selection, system instructions, or extending the base agent class for non-LLM logic.
This skill should be used when the user asks about "multi-agent systems", "sub-agents", "delegation", "agent routing", "orchestration", "SequentialAgent", "ParallelAgent", "LoopAgent", "agent-to-agent", "A2A protocol", "agent hierarchy", "streaming", "real-time responses", "SSE", "server-sent events", "websocket", "bidirectional", "Live API", "voice", "audio", "video", "multimodal streaming", or needs guidance on building systems with multiple specialized agents working together or implementing real-time communication patterns.
This skill should be used when the user asks about "deploying", "production", "Agent Engine", "Vertex AI", "Cloud Run", "GKE", "Kubernetes", "hosting", "scaling", "guardrails", "safety", "content filtering", "input validation", "output validation", "authentication", "OAuth", "API keys", "credentials", "security plugins", "testing agents", "evaluation", "evals", "benchmarks", "tracing", "Cloud Trace", "logging", "observability", "AgentOps", "LangSmith", "user simulation", or needs guidance on deploying ADK agents to production environments, implementing safety measures, access control, secure authentication, testing, debugging, monitoring, or evaluating ADK agent quality.
This skill should be used when the user asks about "adding a tool", "FunctionTool", "creating tools", "MCP integration", "OpenAPI tools", "built-in tools", "google_search tool", "code_execution tool", "long-running tools", "async tools", "third-party tools", "LangChain tools", "computer use", or needs guidance on extending agent capabilities with custom functions, API integrations, or external tool frameworks.
| name | CrewAI |
| description | Workflow patterns and gotchas for CrewAI. Directs to RAG for implementation. |
| Need | Component | RAG Query |
|---|---|---|
| Define specialist | Agent | "crewai agent role goal" |
| Define work unit | Task | "crewai task description" |
| Coordinate agents | Crew | "crew process sequential" |
| Custom capabilities | Tool | "crewai custom tool" |
| Structured output | Output schemas | "crewai output pydantic" |
Query RAG: mcp__agentic-rag__query_sdk("component example", sdk="crewai", mode="build")
These define CrewAI success:
sequential vs hierarchical changes everythingRAG Query: mcp__agentic-rag__query_sdk("Agent role goal backstory", sdk="crewai", mode="build")
Each agent needs a clear role, specific goal, and relevant backstory.
RAG Query: mcp__agentic-rag__query_sdk("crewai tool decorator", sdk="crewai", mode="build")
RAG Query: mcp__agentic-rag__query_sdk("Task description expected_output", sdk="crewai", mode="build")
Tasks must specify: description, expected_output, assigned agent.
RAG Query: mcp__agentic-rag__query_sdk("Crew agents tasks process", sdk="crewai", mode="build")
RAG Query: mcp__agentic-rag__query_sdk("crew kickoff inputs", sdk="crewai", mode="build")
| Symptom | Likely Cause | RAG Query |
|---|---|---|
| Agent off-topic | Bad role/goal | "agent role definition" |
| Wrong output format | Missing expected_output | "task expected_output" |
| Infinite delegation | Allow_delegation loop | "delegation control" |
| Tool not used | Unclear tool name | "tool naming crewai" |
| Tasks out of order | Wrong process type | "sequential hierarchical" |
| Type | When to Use | RAG Query |
|---|---|---|
| Sequential | Tasks depend on previous output | "sequential process" |
| Hierarchical | Manager delegates to workers | "hierarchical manager" |
Researcher → Analyst → Writer pipeline.
RAG Query: mcp__agentic-rag__query_sdk("research crew example", sdk="crewai", mode="build")
Triage → Specialist routing.
RAG Query: mcp__agentic-rag__query_sdk("support crew routing", sdk="crewai", mode="build")
Query RAG when you need:
"crewai memory persistence""crewai task callbacks""crewai async kickoff""crewai custom llm""crewai pydantic output"