Runpodctl is a command-line tool designed for managing GPU pods and serverless endpoints on the Runpod platform. It is particularly useful for developers and data scientists who need to deploy and manage AI workloads efficiently.
$ npx skills add https://github.com/runpod/skills --skill runpodctlRunpodctl is a command-line interface tool that enables developers and data scientists to manage GPU pods, serverless endpoints, templates, volumes, and models on the Runpod platform. The tool provides comprehensive commands for creating, listing, updating, and deleting GPU workloads across Linux, macOS, and Windows. You can deploy containerized applications using custom Docker images or pre-configured templates, search the Runpod Hub marketplace for deployable repositories, and configure scaling policies and resource allocation for serverless endpoints. Runpodctl streamlines GPU resource management, making it easier to provision and monitor AI workloads without navigating the web console.
Install using the official installer or Homebrew for macOS.
Deploying models on serverless GPU endpoints
Managing GPU pods and templates
Handling serverless workloads effectively
Integrating with other Runpod CLI tools
$ npx skills add https://github.com/runpod/skills --skill runpodctlgit clone https://github.com/runpod/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Check the GitHub repository or documentation for usage examples.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan