NeVibeCode · repository · 18 items
runpod-plugins-official: a set by runpod
The runpod/runpod-plugins-official repository on GitHub: 18 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- runpod/runpod-plugins-official
- Stars
- ★ 50
- Installs across cards
- 129,253
- License
- Apache-2.0
- Source updated
- 2026-11-14
- In the catalog since
- 2026-10-25
flash skill Writes and deploys Runpod Serverless with runpod-flash: @Endpoint decorators, local iteration, and shipping endpoints.
CX Codex +1
14,700installs
runpod skill Routes Runpod infrastructure tasks. Directs multi-step provisioning to the right tool lane or verified end-to-end recipe.
CX Codex +1
14,600installs
runpod-mcp skill Controls Runpod infrastructure via the Runpod MCP server. Handles requests for pods, serverless endpoints, templates, network volumes, and GPU catalog checks.
CX Codex +1
14,500installs
runpod-usage skill runpod-usage — a skill for Claude Code that explains Runpod architecture and workload choices. It covers Pods, Serverless, GPUs, storage, networking, and image builds.
CX Codex +1
14,500installs
companion-clis skill companion-clis is a skill that guides agents through HuggingFace, GitHub, Docker, and AWS CLIs for Runpod tasks involving models, repositories, images, and network volumes.
CX Codex +1
14,300installs
runpod-migrate skill runpod-migrate migrates Runpod GraphQL API and REST v1 code to REST v2, locating call sites and breaking changes. Use it before an API upgrade or to identify the API generation in a repository.
CX Codex +1
12,800installs
runpod-templates skill runpod-templates — a skill for Claude Code, Codex, Cursor and other AI editors that lets you discover, understand, and deploy official Runpod Pod templates, with tools to repair ComfyUI workflow model metadata.
CX Codex +1
12,100installs
serverless-deploy skill serverless-deploy is a Claude Code skill that deploys an existing model, workflow, or container to Runpod Serverless and tests the endpoint with a real job.
CX Codex +1
3,700installs
pod-deploy skill pod-deploy provisions a GPU or CPU machine on Runpod and returns the working address. Confirms GPU class availability in the target data center before creating the Pod.
CX Codex +1
3,700installs
pod-doctor skill pod-doctor diagnoses unreachable, stuck, or GPU-blind Runpod Pods using MCP tools. Inspects logs in read-only mode and suggests safe recoveries without data loss.
CX Codex +1
3,700installs
endpoint-ops skill endpoint-ops is a Claude Code skill that diagnoses queues and failing workers on an existing Runpod Serverless endpoint. It also handles requested endpoint setting changes.
CX Codex +1
3,700installs
lifecycle-crud skill lifecycle-crud is a Claude Code skill for managing Runpod resources. It provisions GPU infrastructure and stages models on volumes.
CX Codex +1
3,700installs
discovery skill discovery queries Runpod GPU and CPU catalogs, checks live stock per data center, sizes model VRAM, and quotes prices without deploying machines.
CX Codex +1
3,700installs
cost-audit skill The cost-audit skill breaks down Runpod charges by resource and investigates spend from idle Pods or serverless workers. Use it to trace what is driving an account bill.
CX Codex +1
3,700installs
runpod-build-template skill runpod-build-template is a Claude Code skill that creates or improves complete Runpod template projects, including Dockerfiles, app configuration, and deployment setup for Pod or Serverless.
CX Codex +1
3,200installs
runpod-lifecycle-crud skill The runpod-lifecycle-crud Claude Code skill manages Runpod resources through MCP tools. It creates and checks volumes, templates, secrets, and clusters, and reads account records.
CX Codex +1
1,000installs
runpod-flash skill runpod-flash — a skill for Claude Code and Codex that guides code-first serverless development on remote GPUs via Runpod Python SDK 2.0.
CX Codex +1
1,000installs
runpod-vllm skill runpod-vllm — a Claude Code skill that deploys and tests a vLLM server for a Hugging Face model on RunPod. It activates for requests to deploy, serve, or test an LLM with vLLM, and to troubleshoot a deployment that will not boot.
CX Codex +1
653installs