Skip to content
TrustedSkillsbeta
Back to all skills

Skypilot Multi Cloud Orchestration

Listed
davila7·vlatest·cloud·MIT

Skypilot Multi Cloud Orchestration automates deployments across various clouds, simplifying infrastructure management and accelerating application delivery.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add davila7/claude-code-templates --skill skypilot-multi-cloud-orchestration -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

davila7

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No credential access: failed

    Touches credential material in 3 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found

    • cli-tool/components/skills/ai-research/infrastructure-skypilot/references/advanced-usage.md:305Kubernetes credentials
      export KUBECONFIG=~/.kube/config
    • cli-tool/components/skills/ai-research/infrastructure-skypilot/references/troubleshooting.md:24Kubernetes credentials
      export KUBECONFIG=~/.kube/config
    • cli-tool/components/skills/ai-research/infrastructure-skypilot/references/troubleshooting.md:439SSH private keys or config
      ls -la ~/.ssh/sky-key*

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 1 place.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found

    • cli-tool/components/skills/ai-research/infrastructure-skypilot/references/troubleshooting.md:181pip install straight from a URL
      pip install torch==2.1.0+cu121 -f https://download.pytorch.org/whl/torch_stable.html

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • Pinned to a commit: passed

    Scanned davila7/claude-code-templates at 79182c51fb.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
79182c51fb
Manifest
cli-tool/components/skills/ai-research/infrastructure-skypilot/SKILL.md
Scanned
3 files, 1,381 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

Skypilot Multi-Cloud Orchestration enables AI agents to automate deployments and manage machine learning (ML) workloads across a wide range of cloud providers, including AWS, GCP, Azure, Kubernetes, Lambda, and RunPod. It simplifies infrastructure management by automatically selecting the cheapest available cloud region and leveraging spot instances for significant cost savings. The skill also supports distributed training and model serving with autoscaling capabilities.

When to use it

  • Running machine learning workloads across multiple clouds (AWS, GCP, Azure).
  • Optimizing costs through automatic selection of the most affordable cloud regions.
  • Executing long-running jobs on spot instances while ensuring auto-recovery in case of interruptions.
  • Managing distributed multi-node training tasks.
  • Seeking a unified interface for managing resources across 20+ different cloud providers and avoiding vendor lock-in.

Key capabilities

  • Multi-cloud support: Works with AWS, GCP, Azure, Kubernetes, Lambda, RunPod, and 20+ other providers.
  • Cost optimization: Automatically selects the cheapest available cloud region.
  • Spot instance utilization: Leverages spot instances for up to 3-6x cost savings with automatic recovery.
  • Distributed training: Supports multi-node jobs with gang scheduling.
  • Managed Jobs: Provides auto-recovery, checkpointing, and fault tolerance features.
  • Model Serving (Sky Serve): Enables model serving with autoscaling capabilities.

Example prompts

  • "Launch a cluster on the cheapest available cloud region using 4 A100 GPUs."
  • "Run my training script (train.py) on a cluster with two nodes, utilizing spot instances for cost optimization."
  • "Deploy my model endpoint and enable autoscaling to handle varying request loads."

Tips & gotchas

  • Installation requires pip install "skypilot[aws,gcp,azure,kubernetes]". Ensure you have the necessary cloud provider credentials configured.
  • SkyPilot integrates with a task YAML file which defines resource requirements and commands. Understanding this structure is crucial for effective use.
  • Consider alternatives like Modal or Ray if your needs are simpler or more focused on specific serverless GPU environments or pure Ray-based orchestration, respectively.