Agent skill · google
agents-cli-langchain
Use when working in this project — adding tools, editing the agent, running, evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent, google.adk, adk web, or an ADK runner. This project is LangChain/LangGraph scaffolded by agents-cli, so ADK-specific instructions do not apply.
What it needs
About 2k tokens when loaded.
What this skill does
LangChain project (agents-cli) The agent is a compiled LangGraph graph exported as rootagent from app/agent.py. There is no google.adk dependency and no ADK runner. Other google-agents-cli- skills assume ADK; where they describe the agent itself, this skill wins. Experimental, and Agent Runtime is degraded. Deploy to cloudrun or gke. On agentruntime the app serves, but publish gemini-enterprise is refused, the Console playground cannot invoke it, and Console sessions/traces stay empty: all three want the ADK reasoningengine routes this project does not serve. Say so before recommending it. What ADK guidance maps to here ADK guidance This project --- --- LlmAgent, Agent, google.adk.tools langchain.agents.createagent, plain Python functions as tools, or any compiled StateGraph adk web, adk run agents-cli playground (runs langgraph dev) ADK runner behind agents-cli run agents-cli run invokes the graph in-process agents-cli eval dataset synthesize, eval optimize Unavailable: both drive the agent through ADK. The command says so and exits Add an LlmAgent in app/agent.py Change the graph in app/agent.py; keep the name rootagent The contract Keep these two, whatever you build inside them: app/agent.py exports rootagent, a compiled graph with messages state. Callers only use rootagent.invoke({"messages": [...]}) and rootagent.astream(streammode="messages"). app/fastapiapp.py exposes app. Every deployment target runs uvicorn app.fastapiapp:app. Adding a tool means writing a typed function with a docstring and passing it in tools=[...]. Switching frameworks (LangGraph StateGraph, deepagents.createdeepagent) means rewriting app/agent.py only. Pre-1.0 LangChain (LCEL chains, AgentExecutor) is not supported: not compiled graphs. Commands playground, run and eval generate are overridden by agents-cli-extension.yaml at the project root. Prefix any command with AGENTSCLIDISABLEOVERRIDES=1 to reach the built-in instead. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills google/agents-cli-langchain