10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 622 ms

1. 1runpodverified and signedpassport

   skillrunpod/runpod-plugins-officialrecord

   • runpod

     Start here for any Runpod task — running GPU/CPU pods, deploying serverless endpoints, templates, network volumes, building images, or understanding how Runpod works. Routes to the right skill (runpod-mcp, runpodctl, flash, companion-clis, runpod-usage, runpod-templates, runpod-migrate) and indexes

2. 2runpodverified and signedpassport

   skilldigitalsamba/claude-code-video-toolkitrecord

   • runpod

     Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5 toolkit images (qwen-edit, realesrgan, propainter, sadtalker, qwen3-tts).

3. 3runpod-usageverified and signedpassport

   skillrunpod/runpod-plugins-officialrecord

   • runpod-usage

     How Runpod works and how to work it — pods vs serverless, GPU/VRAM selection, storage, building a container, networking, plus the agentic pod development loop (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene (uv/apt). Use to answer "how does X work", "which GPU", "how do I

4. 4runpod-templatesverified and signedpassport

   skillrunpod/runpod-plugins-officialrecord

   • runpod-templates

     Runpod's official prebuilt pod templates (ComfyUI, PyTorch, and others): what each image ships, which ports and paths it uses, how to pick one, how to pin a version, and what is missing on first boot. Use when a task says "run <X> on a pod" and an official template already covers it, instead of buil

5. 5runpod-mcpverified and signedpassport

   skillrunpod/runpod-plugins-officialrecord

   • runpod-mcp

     Manage Runpod infrastructure through the connected Runpod MCP server's tool calls (pods, serverless endpoints and jobs, templates, network volumes, registry credentials, secrets, clusters, the GPU/CPU catalog, and billing), and connect the server when it is missing (hosted or local npx). Load it bef

6. 6RunPod MCP Serverfound in code, not yet checkedno passport yet
   • start-pod

7. 7runpodctlverified and signedpassport

   skillrunpod/runpod-plugins-officialrecord

   • runpodctl

     Runpod CLI for managing GPU/CPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send/receive). Use for terminal/CI/scripting, Hub browse/deploy, SSH setup, `doctor`, or when the Runpod MCP tools are not connected. For

8. 8runpod-mcpfound in code, not yet checkedno passport yet
   • pod_status

     Pod state (no_pod / stopped / running / running_ssh_pending) + driver, disk, active jobs, $/hr for one vehicle's pod. Read-only.

9. 9runpod-migrateverified and signedpassport

   skillrunpod/runpod-plugins-officialrecord

   • runpod-migrate

     Migrate a codebase from the Runpod GraphQL API or REST v1 to REST v2 — inventory which parts use which API version, rewrite the call sites, flag breaking changes, and verify. Use when someone asks to move to v2, asks what v2 would change, or asks which Runpod API their code is on. For managing infra

10. 10runpod-helperfound in code, not yet checkedno passport yet

    MCP serverdeduzzo/runpod-helper

    • up

      Avvia il Pod (COSTA). Richiede gpu scelta dall'utente, confirm: true e expectedHourlyUSD uguale a quello di up_preview (se il prezzo è cambiato: errore). Parte in background: restituisce jobId. wait: true con una GPU di `waitable` (non disponibile ora): il job verifica la disponibilità ogni 10 s e c