Claude Skills by eformat

Deploy a scaffolded agent to OpenShift using a UBI 9 Python S2I build. Run when the user asks to deploy, build, or run an agent on OpenShift.

Add a secure code sandbox to a scaffolded agent. Inserts the run_code tool into agent.py, starts the sandbox, runs verification tests, and optionally adds MLflow tracing for full observability. Run when the user asks to add code execution, a sandbox, or a code interpreter to an agent.

Use when adding a new documentation page to the AgentOps site — creating MDX content pages with code examples, Demo components, CodeBlock snippets, framework cards, and navigation updates. Triggers on requests like "add a page for X", "create content for Y", "new topic page", or expanding stub pages into full content.

Scaffold a basic AutoGen agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, generate, or scaffold an AutoGen agent.

Scaffold a basic CrewAI agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, generate, or scaffold a CrewAI agent.

Scaffold a basic Google ADK agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, generate, or scaffold a Google ADK agent.

Scaffold a basic LangChain/LangGraph ReAct agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, generate, or scaffold a LangChain or LangGraph agent.

Scaffold a basic LlamaIndex ReAct agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, generate, or scaffold a LlamaIndex agent.

Add MLflow tracing to a scaffolded agent. Inserts the MLflow init block into agent.py and updates requirements. Run when the user asks to add tracing, connect to MLflow, or enable observability for an agent.