Use when implementing a LangChain-based agent runtime from an approved ai-architecture.md agent control-flow design. Produces graph or chain structure, tool registry, memory and session handling, stop conditions, max-step enforcement, failure recovery, tracing, and tests for tool loops, unsafe actions, and fallback behavior. Do not use for deciding whether an agent is needed, designing the tool surface, generic RAG, or direct provider SDK integration.
$npx -y skills add amritmalla/claude-full-stack-2.0 --skill langchain-agent-runtimeInstalls into the current project.
Run `npx skills use "https://github.com/amritmalla/claude-full-stack-2.0" --skill "amritmalla/claude-full-stack-2.0/langchain-agent-runtime"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/amritmalla/claude-full-stack-2.0" that are relevant to the current task. Run `npx skills add "https://github.com/amritmalla/claude-full-stack-2.0"` and select the relevant skills, then follow their instructions.