跳至主要内容
小龙虾小龙虾AI
🤖

RunPod pod management

Manage RunPod GPU cloud instances - create, start, stop, connect to pods via SSH and API. Use when working with RunPod infrastructure, GPU instances, or need SSH access to remote GPU machines. Handles pod lifecycle, SSH proxy connections, filesystem mounting, and API queries. Requires runpodctl (brew install runpod/runpodctl/runpodctl).

下载884
星标0
版本1.0.1
开发工具
安全通过
💬Prompt

技能说明


name: runpod description: Manage RunPod GPU cloud instances - create, start, stop, connect to pods via SSH and API. Use when working with RunPod infrastructure, GPU instances, or need SSH access to remote GPU machines. Handles pod lifecycle, SSH proxy connections, filesystem mounting, and API queries. Requires runpodctl (brew install runpod/runpodctl/runpodctl).

RunPod Skill

Manage RunPod GPU cloud instances, SSH connections, and filesystem access.

Prerequisites

brew install runpod/runpodctl/runpodctl
runpodctl config --apiKey "your-api-key"

SSH Key: runpodctl manages SSH keys in ~/.runpod/ssh/:

runpodctl ssh add-key

View and manage keys at: https://console.runpod.io/user/settings

Mount script configuration: The mount script checks ~/.ssh/runpod_key first, then falls back to runpodctl's default key. Override with:

export RUNPOD_SSH_KEY="$HOME/.runpod/ssh/RunPod-Key"

Host keys are stored separately in ~/.runpod/ssh/known_hosts (isolated from your main SSH config). Uses StrictHostKeyChecking=accept-new to verify hosts on reconnect while allowing new RunPod instances.

Quick Reference

runpodctl get pod                    # List pods
runpodctl get pod <id>               # Get pod details
runpodctl start pod <id>             # Start pod
runpodctl stop pod <id>              # Stop pod
runpodctl ssh connect <id>           # Get SSH command
runpodctl send <file>                # Send file to pod
runpodctl receive <code>             # Receive file from pod

Common Operations

Create Pod

# Without volume
runpodctl create pod --name "my-pod" --gpuType "NVIDIA GeForce RTX 4090" --imageName "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404"

# With volume (100GB at /workspace)
runpodctl create pod --name "my-pod" --gpuType "NVIDIA GeForce RTX 4090" --imageName "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404" --volumeSize 100 --volumePath "/workspace"

Important: When using a volume (--volumeSize), always specify --volumePath too. Without it:

error creating container: ... invalid mount config for type "volume": field Target must not be empty

SSH to Pod

# Get SSH command
runpodctl ssh connect <pod_id>

# Connect directly (copy command from above)
ssh -p <port> root@<ip> -i ~/.ssh/runpod_key

Mount Pod Filesystem (SSHFS)

./scripts/mount_pod.sh <pod_id> [base_dir]

Mounts pod to ~/pods/<pod_id> by default.

Access files:

ls ~/pods/<pod_id>/
cat ~/pods/<pod_id>/workspace/my-project/train.py

Unmount:

fusermount -u ~/pods/<pod_id>

Helper Script

ScriptPurpose
mount_pod.shMount pod filesystem via SSHFS (no runpodctl equivalent)

Web Service Access

Proxy URLs:

https://<pod_id>-<port>.proxy.runpod.net

Common ports:

  • 8188: ComfyUI
  • 7860: Gradio
  • 8888: Jupyter
  • 8080: Dev tools

如何使用「RunPod pod management」?

  1. 打开小龙虾AI(Web 或 iOS App)
  2. 点击上方「立即使用」按钮,或在对话框中输入任务描述
  3. 小龙虾AI 会自动匹配并调用「RunPod pod management」技能完成任务
  4. 结果即时呈现,支持继续对话优化

相关技能