How do I install the Ops Runpod skill?

Run npx skillmds add majiayu000/ops-runpod in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ops Runpod safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ops Runpod?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ops Runpod free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ops Runpod?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ops Runpod by majiayu000 — Agent Skill

Name: Ops Runpod
Rating: 4.666666666666667 (3 reviews)
Author: majiayu000

Ops Runpod

Provision, manage, and terminate RunPod GPU instances for LLM training. Use when user says "spin up GPU", "create RunPod instance", "terminate pod", "check GPU status", "provision training server", or needs cloud GPU resources.

majiayu000 b198f45 2 files · 3.2 KB Updated Sep 9, 2026 567 repo stars

File contents

RunPod Operations Skill

Manage RunPod GPU instances for LLM training and inference.

Self-contained skill - auto-installs via uv run from git (no pre-installation needed).

Quick Start

# Via wrapper (auto-installs from GitHub on demand)
.agents/skills/ops-runpod/run.sh list-instances

# Create an instance
.agents/skills/ops-runpod/run.sh create-instance 70B --hours 4

# Monitor an instance
.agents/skills/ops-runpod/run.sh monitor <pod-id>

# Terminate an instance
.agents/skills/ops-runpod/run.sh terminate <pod-id>

Commands

Command	Purpose
`create-instance`	Create GPU pod optimized for model size
`list-instances`	Show all running pods with status/cost
`monitor`	Live monitoring of pod metrics
`terminate`	Safely terminate a pod
`estimate-cost`	Estimate training cost before creating
`optimize`	Find optimal GPU config using benchmarks
`start-training`	Start a training job on RunPod
`serve`	Start inference server on RunPod

Examples

Create Instance

.agents/skills/ops-runpod/run.sh create-instance 70B --hours 4

Returns: pod_id=abc123


### Estimate Cost
```bash
.agents/skills/ops-runpod/run.sh estimate-cost 70B --hours 8

Monitor Instance

.agents/skills/ops-runpod/run.sh monitor <pod-id>

Terminate Instance

.agents/skills/ops-runpod/run.sh terminate <pod-id>

Environment Variables

Variable	Required	Description
`RUNPOD_API_KEY`	Yes	RunPod API key

Typical Workflow

# 1. Estimate cost
.agents/skills/ops-runpod/run.sh estimate-cost 70B --hours 8

# 2. Create pod
.agents/skills/ops-runpod/run.sh create-instance 70B --hours 8

# 3. Monitor or SSH into pod
.agents/skills/ops-runpod/run.sh monitor <pod-id>

# 4. Run training...

# 5. Terminate when done
.agents/skills/ops-runpod/run.sh terminate <pod-id>

Integration with Memory

After training completes, log the lesson:

memory-agent learn \
  --problem "Training Qwen3-70B on RunPod" \
  --solution "Used A100-80GB, 8 hours, cost $24.72. Config: lr=2e-5, batch=4"

---name: ops-runpoddescription: Provision, manage, and terminate RunPod GPU instances for LLM training. Use when user says "spin up GPU", "create RunPod instance", "terminate pod", "check GPU status", "provision training server", or needs cloud GPU resources.--- # RunPod Operations Skill Manage RunPod GPU instances for LLM training and inference. **Self-contained skill** - auto-installs via `uv run` from git (no pre-installation needed). ## Quick Start ```bash # Via wrapper (auto-installs from GitHub on demand) .agents/skills/ops-runpod/run.sh list-instances # Create an instance .agents/skills/ops-runpod/run.sh create-instance 70B --hours 4 # Monitor an instance .agents/skills/ops-runpod/run.sh monitor <pod-id> # Terminate an instance .agents/skills/ops-runpod/run.sh terminate <pod-id> ``` ## Commands | Command | Purpose | |---------|---------| | `create-instance` | Create GPU pod optimized for model size | | `list-instances` | Show all running pods with status/cost | | `monitor` | Live monitoring of pod metrics | | `terminate` | Safely terminate a pod | | `estimate-cost` | Estimate training cost before creating | | `optimize` | Find optimal GPU config using benchmarks | | `start-training` | Start a training job on RunPod | | `serve` | Start inference server on RunPod | ## Examples ### Create Instance .agents/skills/ops-runpod/run.sh create-instance 70B --hours 4 # Returns: pod_id=abc123 ``` ### Estimate Cost ```bash .agents/skills/ops-runpod/run.sh estimate-cost 70B --hours 8 ``` ### Monitor Instance ```bash .agents/skills/ops-runpod/run.sh monitor <pod-id> ``` ### Terminate Instance ```bash .agents/skills/ops-runpod/run.sh terminate <pod-id> ``` ## Environment Variables | Variable | Required | Description | |----------|----------|-------------| | `RUNPOD_API_KEY` | Yes | RunPod API key | ## Typical Workflow ```bash # 1. Estimate cost .agents/skills/ops-runpod/run.sh estimate-cost 70B --hours 8 # 2. Create pod .agents/skills/ops-runpod/run.sh create-instance 70B --hours 8 # 3. Monitor or SSH into pod .agents/skills/ops-runpod/run.sh monitor <pod-id> # 4. Run training... # 5. Terminate when done .agents/skills/ops-runpod/run.sh terminate <pod-id> ``` ## Integration with Memory After training completes, log the lesson: ```bash memory-agent learn \ --problem "Training Qwen3-70B on RunPod" \ --solution "Used A100-80GB, 8 hours, cost $24.72. Config: lr=2e-5, batch=4" ```

Frequently asked questions