runpod

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).

3,891 stars

byopenclaw

View on GitHub Installation ↓

Best use case

runpod is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using runpod should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/runpod/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/andrewharp/runpod/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/runpod/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How runpod Compares

Feature / Agent	runpod	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

AI Agents for Startups

Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

SKILL.md Source

# RunPod Skill

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

## Prerequisites

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

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

```bash
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:
```bash
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

```bash
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

```bash
# 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

```bash
# 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)

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

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

**Access files:**
```bash
ls ~/pods/<pod_id>/
cat ~/pods/<pod_id>/workspace/my-project/train.py
```

**Unmount:**
```bash
fusermount -u ~/pods/<pod_id>
```

## Helper Script

| Script | Purpose |
|--------|---------|
| `mount_pod.sh` | Mount 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

Related Skills

---

3891

from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891

from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891

from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891

from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891

from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891

from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891

from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891

from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891

from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure