google-adk
Workflow patterns and gotchas for Google Agent Development Kit. Directs to RAG for implementation.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Workflow patterns and gotchas for Google Agent Development Kit. Directs to RAG for implementation.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | Google ADK |
| description | Workflow patterns and gotchas for Google Agent Development Kit. Directs to RAG for implementation. |
| Need | Agent Type | RAG Query |
|---|---|---|
| LLM reasoning with tools | LlmAgent | "LlmAgent configuration" |
| Custom non-LLM logic | BaseAgent | "BaseAgent implementation" |
| Sequential pipeline | SequentialAgent | "SequentialAgent example" |
| Parallel execution | ParallelAgent | "ParallelAgent concurrent" |
| Iteration patterns | LoopAgent | "LoopAgent termination" |
Query RAG: mcp__agentic-rag__query_sdk("agent type example", sdk="adk", mode="build")
These are NOT in docs or easy to discover:
root_agent - ADK expects this exact name in agent.pyGOOGLE_API_KEY=value not GOOGLE_API_KEY="value"RAG Query: mcp__agentic-rag__query_sdk("ADK project structure", sdk="adk", mode="explain")
RAG Query: mcp__agentic-rag__query_sdk("LlmAgent basic example", sdk="adk", mode="build")
RAG Query: mcp__agentic-rag__query_sdk("function tool definition", sdk="adk", mode="build")
Remember: Every tool needs a docstring with Args and Returns.
RAG Query: mcp__agentic-rag__query_sdk("agent state management", sdk="adk", mode="build")
RAG Query: mcp__agentic-rag__query_sdk("sub_agents routing", sdk="adk", mode="build")
RAG Query: mcp__agentic-rag__query_sdk("ADK testing", sdk="adk", mode="explain")
| Symptom | Likely Cause | RAG Query |
|---|---|---|
| Tool not invoked | Missing/bad docstring | "tool docstring format" |
| Import error | Wrong module path | "ADK imports" |
| Auth failure | .env formatting | "ADK authentication" |
| Sub-agent ignored | Poor description | "sub_agents description" |
| State not persisting | Wrong state access | "ToolContext state" |
Query RAG when you need:
"ADK streaming response""agent to agent protocol""ADK visual builder""ADK callbacks events""ADK session memory"