skills.rest
ClawLink-HQ
ClawLink-HQOFFICIAL
Explore all skills by this author →
Website𝕏@clawlinkdevGitHub

runpod-compute

Manage RunPod clusters, serverless endpoints, templates, and secrets.

117|10|Updated Mar 29, 2026
Search Tags:#secret management#template management#cluster management#runpod#serverless endpoints
One-click install
npx skills add https://github.com/ClawLink-HQ/clawlink --skill runpod-compute
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: runpod-compute
Source: https://github.com/ClawLink-HQ/clawlink/tree/main/clawhub-skills/runpod-compute
Command: npx skills add https://github.com/ClawLink-HQ/clawlink --skill runpod-compute

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill simplifies the process of managing RunPod clusters, serverless endpoints, templates, and secrets for ML inference and distributed computing workloads, eliminating the need for manual API configurations.

Core Features & Use Cases

  • Cluster Management: Create and manage GPU clusters for distributed computing.
  • Serverless Endpoints: Configure and manage serverless endpoints for scalable compute resources.
  • Template Management: Create and update templates for consistent deployment.
  • Secrets Management: Store and manage secrets securely.
  • Use Case: For data scientists who need to quickly set up GPU-accelerated environments for machine learning tasks without worrying about infrastructure setup.

Quick Start

Use the runpod-compute skill to create a new GPU cluster with the command: clawlink_call_tool --tool "runpod_create_cluster" --params '{"name": "my-cluster", "gpu_type_id": "RTX_4090", "node_count": 2}'.

Frequently Asked Questions about runpod-compute

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate RunPod cluster management for GPU-accelerated compute?▼

You can automate RunPod cluster management by using this Skill to programmatically create, update, and delete GPU clusters through the RunPod API, eliminating the need for manual API configurations.

What is the best way to set up serverless endpoints for ML inference without manual infrastructure configuration?▼

Setting up serverless endpoints for ML inference is best handled by automating the process with this Skill, which configures scalable compute resources and deploys templates directly via API key authentication.

Do I need an API key to manage RunPod serverless endpoints and templates?▼

Yes, API key authentication is required to manage RunPod serverless endpoints, create templates, and handle secrets, ensuring secure access to your GPU-accelerated compute resources.

Can I securely manage secrets for distributed computing workloads on RunPod?▼

You can securely manage secrets for distributed computing workloads by using this Skill's dedicated secrets management feature to store and manage credentials needed for your ML environments.

Does RunPod compute management integrate with hosted connection flows for automated deployments?▼

Yes, RunPod compute management integrates with OpenClaw and Hermes for hosted connection flows, streamlining automated deployments of serverless endpoints and clusters.

Related Skills

Explore More Software Engineering Skills→
Zayne-spragueZayne-sprague
5

cluster-setup

Configure and validate SLURM, RunPod, or local clusters in RACA.

Community
Advanced
ovachieverovachiever
52

modal

Run Python code in the cloud with autoscaling and GPU acceleration via Modal's serverless platform.

Community
Advanced
paarths-collabpaarths-collab
13

integration-postgres

Connect a PostgreSQL database to a self-hosted Hermes agent over SSH.

Community
Advanced
nelohenriqnelohenriq
1

modal-serverless-gpu

Deploy ML models as scalable APIs with serverless GPU compute.

Community
Advanced