메뉴
Systematic debugging workflow for all agentic frameworks. Directs to RAG for solutions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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 | Agent Debugging |
| description | Systematic debugging workflow for all agentic frameworks. Directs to RAG for solutions. |
| Category | Symptoms | First Checks |
|---|---|---|
| IMPORT | ModuleNotFoundError, ImportError | pip list, venv active, import paths |
| TOOL | "tool not found", wrong args | docstrings, decorators, registration |
| AUTH | 401, 403, "invalid key" | .env exists, env vars set, key format |
| CONFIG | "missing config", wrong values | .env format (no quotes!), required fields |
| RUNTIME | Unexpected behavior, crashes | logs, state inspection, callbacks |
| MULTI_AGENT | Wrong routing, delegation fails | agent descriptions, routing logic |
| STREAMING | Connection issues, timeouts | SSE config, network, timeout settings |
Enable verbose/trace mode for the framework.
RAG Query: mcp__agentic-rag__search("[framework] debugging tracing", mode="explain")
Match symptoms to category above. This determines the fix strategy.
RAG Query: mcp__agentic-rag__search("error: [error message]", mode="explain")
Check framework-specific gotchas in the relevant @framework skill.
pip list | grep [package])RAG Query: mcp__agentic-rag__search("[framework] installation imports", mode="explain")
RAG Query: mcp__agentic-rag__search("tool definition", mode="build")
RAG Query: mcp__agentic-rag__search("[framework] authentication", mode="explain")
RAG Query: mcp__agentic-rag__search("agent routing delegation", mode="build")
| Framework | How to Enable Tracing | RAG Query |
|---|---|---|
| ADK | Tracing plugins | "ADK tracing debugging" |
| OpenAI | Debug env var | "openai agents debug" |
| LangChain | LangSmith / set_debug | "langchain tracing langsmith" |
| LangGraph | LangSmith | "langgraph debugging" |
| CrewAI | verbose=True | "crewai verbose debugging" |
| Anthropic | Logging | "anthropic logging debug" |
| Problem | Typical Fix |
|---|---|
| Missing module | pip install [package] + check venv |
| Tool ignored | Add/fix docstring with Args/Returns |
| Auth failure | Check .env format, no quotes |
| Wrong agent called | Make descriptions more specific |
| State lost | Check state passing between nodes/agents |
| Infinite loop | Add termination condition, max iterations |
mcp__agentic-rag__query_docs("exact error message")