LangGraph Agent Skill

This skill provides a LangGraph-based agent framework for consistent tool calling across all OpenAI-compatible LLM providers.

When to Use

• You need guaranteed tool calling consistency (especially with GLM-5, Zhipu, or other models with inconsistent tool invocation)
• You want automatic tool loops that keep calling tools until the task is complete
• You're working with multiple LLM providers and need a unified interface
• You need to build custom agents with specific tool sets

Capabilities

• create_agent: Create a LangGraph agent with custom tools
• run_agent: Execute a task with the agent
• add_tool: Add a custom tool to an agent
• get_agent_result: Retrieve the final result from agent execution

Environment Variables