New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

SkyPilot Multi-Cloud Orchestration

by Orchestra-Research in Orchestra-Research/AI-Research-SKILLs

Runs ML training and batch jobs across clouds with SkyPilot, using spot instances, automatic region selection and managed recovery to cut GPU cost.

MITAuto-check passedDevOps & Cloud

Install SkyPilot Multi-Cloud Orchestration

skills CLI
$ npx skills add Orchestra-Research/AI-Research-SKILLs --skill skypilot-multi-cloud-orchestration -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Orchestra-Research/AI-Research-SKILLs skypilot-multi-cloud-orchestration --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/09-infrastructure/skypilot .claude/skills/skypilot-multi-cloud-orchestration && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skypilot-multi-cloud-orchestration
GitHub stars
13k
Used in
4 other repos
Token cost
~2.4k tokens
SKILL.md length
378 words
Files
3 (incl. references)
Skills in repo
96
Repo updated
First seen
Licence
MIT

At a glance

Runs ML training and batch jobs across clouds with SkyPilot, using spot instances, automatic region selection and managed recovery to cut GPU cost.

  • Launching multi-node training across several cloud providers
  • SKILL.md covers When to use SkyPilot, Quick start, Core concepts and GPU configuration, plus 5 more sections
  • Calls ssh, python and pip; needs HF_TOKEN and WANDB_API_KEY
  • Running long jobs on spot instances with automatic recovery

What it does

The skill is a guide to SkyPilot for ML workloads that span clouds. It lists when SkyPilot fits: jobs across AWS, GCP, Azure, Kubernetes and other providers, automatic selection of the cheapest cloud and region, long jobs on spot instances with auto-recovery, and distributed multi-node training. It names alternatives for simpler cases: Modal for serverless GPU, RunPod for single-cloud pods, Kubernetes for existing clusters and Ray for pure Ray orchestration.

Practical content includes installing with `pip install` and cloud extras, a hello-world task YAML, the main commands (`sky launch`, `sky exec`, `sky status`, `sky stop`, `sky down`, `sky logs`, `sky queue`, `sky jobs launch` and `sky serve up`), GPU selection with accelerator fallbacks, and spot configuration. Sky Serve covers model serving with autoscaling, and two reference files cover advanced usage and troubleshooting. The excerpt is cut off in the cluster management section.

When your agent uses it

  • Launching multi-node training across several cloud providers
  • Running long jobs on spot instances with automatic recovery
  • Picking the cheapest cloud and region for GPU work

Example prompts

  • “Write a SkyPilot task YAML that trains on a single T4 and launch it.”
  • “Move my fine-tuning job to spot A100s with auto-recovery and checkpointing.”
  • “Deploy the model behind Sky Serve with autoscaling.”

Requirements

  • SkyPilot installed with `pip install` and the cloud extras you need
  • Credentials for at least one cloud provider

What it can do on your machine

Read from SKILL.md and the folder at commit 773a529. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ssh
    • python
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • docs.skypilot.co
    • slack.skypilot.co

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN
    • WANDB_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

SkyPilot Multi-Cloud Orchestration loads about 2.4k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 378 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Orchestra-Research/AI-Research-SKILLs at commit 773a529, republished under its MIT licence (© Orchestra-Research). 378 words, ~2,410 tokens.

Download SKILL.mdSave it as .claude/skills/skypilot-multi-cloud-orchestration/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
skypilot-multi-cloud-orchestration
description
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
version
1.0.0
author
Orchestra Research
license
MIT
tags
Infrastructure, Multi-Cloud, Orchestration, GPU, Cost Optimization, SkyPilot
dependencies
skypilot>=0.7.0

SkyPilot Multi-Cloud Orchestration

Comprehensive guide to running ML workloads across clouds with automatic cost optimization using SkyPilot.

When to use SkyPilot

Use SkyPilot when:

  • Running ML workloads across multiple clouds (AWS, GCP, Azure, etc.)
  • Need cost optimization with automatic cloud/region selection
  • Running long jobs on spot instances with auto-recovery
  • Managing distributed multi-node training
  • Want unified interface for 20+ cloud providers
  • Need to avoid vendor lock-in

Key features:

  • Multi-cloud: AWS, GCP, Azure, Kubernetes, Lambda, RunPod, 20+ providers
  • Cost optimization: Automatic cheapest cloud/region selection
  • Spot instances: 3-6x cost savings with automatic recovery
  • Distributed training: Multi-node jobs with gang scheduling
  • Managed jobs: Auto-recovery, checkpointing, fault tolerance
  • Sky Serve: Model serving with autoscaling

Use alternatives instead:

  • Modal: For simpler serverless GPU with Python-native API
  • RunPod: For single-cloud persistent pods
  • Kubernetes: For existing K8s infrastructure
  • Ray: For pure Ray-based orchestration

Quick start

Installation
bash
pip install "skypilot[aws,gcp,azure,kubernetes]"

# Verify cloud credentials
sky check
Hello World

Create hello.yaml:

yaml
resources:
  accelerators: T4:1

run: |
  nvidia-smi
  echo "Hello from SkyPilot!"

Launch:

bash
sky launch -c hello hello.yaml

# SSH to cluster
ssh hello

# Terminate
sky down hello

Core concepts

Task YAML structure
yaml
# Task name (optional)
name: my-task

# Resource requirements
resources:
  cloud: aws              # Optional: auto-select if omitted
  region: us-west-2       # Optional: auto-select if omitted
  accelerators: A100:4    # GPU type and count
  cpus: 8+                # Minimum CPUs
  memory: 32+             # Minimum memory (GB)
  use_spot: true          # Use spot instances
  disk_size: 256          # Disk size (GB)

# Number of nodes for distributed training
num_nodes: 2

# Working directory (synced to ~/sky_workdir)
workdir: .

# Setup commands (run once)
setup: |
  pip install -r requirements.txt

# Run commands
run: |
  python train.py
Key commands
CommandPurpose
sky launchLaunch cluster and run task
sky execRun task on existing cluster
sky statusShow cluster status
sky stopStop cluster (preserve state)
sky downTerminate cluster
sky logsView task logs
sky queueShow job queue
sky jobs launchLaunch managed job
sky serve upDeploy serving endpoint

GPU configuration

Available accelerators
yaml
# NVIDIA GPUs
accelerators: T4:1
accelerators: L4:1
accelerators: A10G:1
accelerators: L40S:1
accelerators: A100:4
accelerators: A100-80GB:8
accelerators: H100:8

# Cloud-specific
accelerators: V100:4         # AWS/GCP
accelerators: TPU-v4-8       # GCP TPUs
GPU fallbacks
yaml
resources:
  accelerators:
    H100: 8
    A100-80GB: 8
    A100: 8
  any_of:
    - cloud: gcp
    - cloud: aws
    - cloud: azure
Spot instances
yaml
resources:
  accelerators: A100:8
  use_spot: true
  spot_recovery: FAILOVER  # Auto-recover on preemption

Cluster management

Launch and execute
bash
# Launch new cluster
sky launch -c mycluster task.yaml

# Run on existing cluster (skip setup)
sky exec mycluster another_task.yaml

# Interactive SSH
ssh mycluster

# Stream logs
sky logs mycluster
Autostop
yaml
resources:
  accelerators: A100:4
  autostop:
    idle_minutes: 30
    down: true  # Terminate instead of stop
bash
# Set autostop via CLI
sky autostop mycluster -i 30 --down
Cluster status
bash
# All clusters
sky status

# Detailed view
sky status -a

Distributed training

Multi-node setup
yaml
resources:
  accelerators: A100:8

num_nodes: 4  # 4 nodes × 8 GPUs = 32 GPUs total

setup: |
  pip install torch torchvision

run: |
  torchrun \
    --nnodes=$SKYPILOT_NUM_NODES \
    --nproc_per_node=$SKYPILOT_NUM_GPUS_PER_NODE \
    --node_rank=$SKYPILOT_NODE_RANK \
    --master_addr=$(echo "$SKYPILOT_NODE_IPS" | head -n1) \
    --master_port=12355 \
    train.py
Show full SKILL.md (155 more words)Show less
Environment variables
VariableDescription
SKYPILOT_NODE_RANKNode index (0 to num_nodes-1)
SKYPILOT_NODE_IPSNewline-separated IP addresses
SKYPILOT_NUM_NODESTotal number of nodes
SKYPILOT_NUM_GPUS_PER_NODEGPUs per node
Head-node-only execution
bash
run: |
  if [ "${SKYPILOT_NODE_RANK}" == "0" ]; then
    python orchestrate.py
  fi

Managed jobs

Spot recovery
bash
# Launch managed job with spot recovery
sky jobs launch -n my-job train.yaml
Checkpointing
yaml
name: training-job

file_mounts:
  /checkpoints:
    name: my-checkpoints
    store: s3
    mode: MOUNT

resources:
  accelerators: A100:8
  use_spot: true

run: |
  python train.py \
    --checkpoint-dir /checkpoints \
    --resume-from-latest
Job management
bash
# List jobs
sky jobs queue

# View logs
sky jobs logs my-job

# Cancel job
sky jobs cancel my-job

File mounts and storage

Local file sync
yaml
workdir: ./my-project  # Synced to ~/sky_workdir

file_mounts:
  /data/config.yaml: ./config.yaml
  ~/.vimrc: ~/.vimrc
Cloud storage
yaml
file_mounts:
  # Mount S3 bucket
  /datasets:
    source: s3://my-bucket/datasets
    mode: MOUNT  # Stream from S3

  # Copy GCS bucket
  /models:
    source: gs://my-bucket/models
    mode: COPY  # Pre-fetch to disk

  # Cached mount (fast writes)
  /outputs:
    name: my-outputs
    store: s3
    mode: MOUNT_CACHED
Storage modes
ModeDescriptionBest For
MOUNTStream from cloudLarge datasets, read-heavy
COPYPre-fetch to diskSmall files, random access
MOUNT_CACHEDCache with async uploadCheckpoints, outputs

Sky Serve (Model Serving)

Basic service
yaml
# service.yaml
service:
  readiness_probe: /health
  replica_policy:
    min_replicas: 1
    max_replicas: 10
    target_qps_per_replica: 2.0

resources:
  accelerators: A100:1

run: |
  python -m vllm.entrypoints.openai.api_server \
    --model meta-llama/Llama-2-7b-chat-hf \
    --port 8000
bash
# Deploy
sky serve up -n my-service service.yaml

# Check status
sky serve status

# Get endpoint
sky serve status my-service
Autoscaling policies
yaml
service:
  replica_policy:
    min_replicas: 1
    max_replicas: 10
    target_qps_per_replica: 2.0
    upscale_delay_seconds: 60
    downscale_delay_seconds: 300
  load_balancing_policy: round_robin

Cost optimization

Automatic cloud selection
yaml
# SkyPilot finds cheapest option
resources:
  accelerators: A100:8
  # No cloud specified - auto-select cheapest
bash
# Show optimizer decision
sky launch task.yaml --dryrun
Cloud preferences
yaml
resources:
  accelerators: A100:8
  any_of:
    - cloud: gcp
      region: us-central1
    - cloud: aws
      region: us-east-1
    - cloud: azure
Environment variables
yaml
envs:
  HF_TOKEN: $HF_TOKEN  # Inherited from local env
  WANDB_API_KEY: $WANDB_API_KEY

# Or use secrets
secrets:
  - HF_TOKEN
  - WANDB_API_KEY

Common workflows

Workflow 1: Fine-tuning with checkpoints
yaml
name: llm-finetune

file_mounts:
  /checkpoints:
    name: finetune-checkpoints
    store: s3
    mode: MOUNT_CACHED

resources:
  accelerators: A100:8
  use_spot: true

setup: |
  pip install transformers accelerate

run: |
  python train.py \
    --checkpoint-dir /checkpoints \
    --resume
Workflow 2: Hyperparameter sweep
yaml
name: hp-sweep-${RUN_ID}

envs:
  RUN_ID: 0
  LEARNING_RATE: 1e-4
  BATCH_SIZE: 32

resources:
  accelerators: A100:1
  use_spot: true

run: |
  python train.py \
    --lr $LEARNING_RATE \
    --batch-size $BATCH_SIZE \
    --run-id $RUN_ID
bash
# Launch multiple jobs
for i in {1..10}; do
  sky jobs launch sweep.yaml \
    --env RUN_ID=$i \
    --env LEARNING_RATE=$(python -c "import random; print(10**random.uniform(-5,-3))")
done

Debugging

bash
# SSH to cluster
ssh mycluster

# View logs
sky logs mycluster

# Check job queue
sky queue mycluster

# View managed job logs
sky jobs logs my-job

Common issues

IssueSolution
Quota exceededRequest quota increase, try different region
Spot preemptionUse sky jobs launch for auto-recovery
Slow file syncUse MOUNT_CACHED mode for outputs
GPU not availableUse any_of for fallback clouds

References

Resources

© Orchestra-Research, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in 09-infrastructure/skypilot of Orchestra-Research/AI-Research-SKILLs.

  • SKILL.md
  • references/advanced-usage.md
  • references/troubleshooting.md

Open the folder on GitHubat commit 773a529

Used in 4 other repositories

We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in Orchestra-Research/AI-Research-SKILLs, which our catalogue first saw on October 7, 2026.

Compare with similar skills

SkyPilot Multi-Cloud Orchestration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

SkyPilot Multi-Cloud Orchestration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SkyPilot Multi-Cloud Orchestration this skillOrchestra-Research/AI-Research-SKILLs13k4 repos~2.4kAutomated safety check: PassMIT
Resource Taggingancoleman/ai-design-components526—~4kAutomated safety check: PassMIT
Optimizing Costsancoleman/ai-design-components526—~5.1kAutomated safety check: PassMIT
Infrastructure Devops Cloud Architectchendongqi/OPB-Skills125—~1.1kAutomated safety check: PassNone
Cloud Cost Optimizationwshobson/agents40k14 repos~1.7kAutomated safety check: PassMIT
Spotinfoalexei-led/spotinfo164—~1.8kAutomated safety check: PassApache-2.0

Similar skills

  • Resource Tagging

    ancoleman/ai-design-components

    Apply and enforce cloud resource tagging strategies across AWS, Azure, GCP, and Kubernetes for cost allocation, ownership tracking, compliance, and automation.

    526 GitHub stars~4k tokensUpdated 10 mo ago
    DevOps & CloudAuto-check passed

  • Optimizing Costs

    ancoleman/ai-design-components

    Optimize cloud infrastructure costs through FinOps practices, commitment discounts, right-sizing, and automated cost management.

    526 GitHub stars~5.1k tokensUpdated 10 mo ago
    DevOps & CloudAuto-check passed

  • Infrastructure Devops Cloud Architect

    chendongqi/OPB-Skills

    云架构助手 - 专业的云计算架构设计与优化专家。适用场景： (1) 云架构设计与方案规划 (2) 云资源选型与容量规划 (3) 云成本优化与FinOps实践 (4) 多云/混合云策略设计 (5) 云迁移方案与实施 (6) 云安全架构设计 (7) 云原生架构转型 触发关键词：云架构、AWS、阿里云、Azure、GCP、云迁移、云成本、多云、混合云、云安全、云原生、Kubernetes、容器

    125 GitHub stars~1.1k tokensUpdated 8 mo ago
    DevOps & CloudAuto-check passed

  • Cloud Cost Optimization

    wshobson/agents

    Cuts cloud spend across AWS, Azure, GCP and OCI with cost tagging, rightsizing, commitment and spot pricing models, and architecture changes.

    40k GitHub starsUsed in 14 repos~1.7k tokens
    DevOps & CloudAuto-check passed

  • Spotinfo

    alexei-led/spotinfo

    Query Spot/preemptible VM prices, savings and interruption risk across AWS, GCP and Azure with the spotinfo CLI.

    164 GitHub stars~1.8k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed

  • Provider Bug Review

    mondoohq/mql

    Deep static code review of an mql provider for logic errors, nil-handling bugs, pagination truncation, caching/id collisions, and other defects that silently give users wrong data.

    412 GitHub stars~2.9k tokensUpdated today
    DevOps & CloudAuto-check passed

More from Orchestra-Research/AI-Research-SKILLs

All 96 skills in this repo

  • AudioCraft Audio Generation

    Orchestra-Research/AI-Research-SKILLs

    Generates music from text descriptions with MusicGen and sound effects with AudioGen, using Meta's AudioCraft PyTorch library with melody and style conditioning.

    13k GitHub starsUsed in 8 repos~3.9k tokens
    Auto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    Auto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    Auto-check passed

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    Auto-check passed

  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    Auto-check passed

  • Whisper Speech Recognition

    Orchestra-Research/AI-Research-SKILLs

    Transcribes audio with OpenAI's Whisper: 99 languages, translation to English, language detection, six model sizes and word-level timestamps, from Python or the CLI.

    13k GitHub starsUsed in 7 repos~1.9k tokens
    Auto-check: notes

Works with

Categories

Questions about SkyPilot Multi-Cloud Orchestration

What does SkyPilot Multi-Cloud Orchestration do?

Runs ML training and batch jobs across clouds with SkyPilot, using spot instances, automatic region selection and managed recovery to cut GPU cost. The skill is a guide to SkyPilot for ML workloads that span clouds. It lists when SkyPilot fits: jobs across AWS, GCP, Azure, Kubernetes and other providers, automatic selection of the cheapest cloud and region, long jobs on spot instances with auto-recovery, and distributed multi-node training.

When should I use SkyPilot Multi-Cloud Orchestration?

SkyPilot Multi-Cloud Orchestration fits situations like: launching multi-node training across several cloud providers; running long jobs on spot instances with automatic recovery; picking the cheapest cloud and region for GPU work.

How do I install SkyPilot Multi-Cloud Orchestration in Claude Code?

Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill skypilot-multi-cloud-orchestration -a claude-code`. Or copy the skill folder (09-infrastructure/skypilot in Orchestra-Research/AI-Research-SKILLs) into .claude/skills/skypilot-multi-cloud-orchestration in your project. Claude Code loads it when a task matches its description.

How do I install SkyPilot Multi-Cloud Orchestration in Codex?

Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill skypilot-multi-cloud-orchestration -a codex`. Or copy the skill folder (09-infrastructure/skypilot in Orchestra-Research/AI-Research-SKILLs) into .agents/skills/skypilot-multi-cloud-orchestration in your project. Codex loads it when a task matches its description.

Can I use SkyPilot Multi-Cloud Orchestration in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill skypilot-multi-cloud-orchestration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skypilot-multi-cloud-orchestration, .gemini/skills/skypilot-multi-cloud-orchestration, .github/skills/skypilot-multi-cloud-orchestration and .opencode/skills/skypilot-multi-cloud-orchestration in your project.

What does SkyPilot Multi-Cloud Orchestration need to run?

Going by SKILL.md and its folder, SkyPilot Multi-Cloud Orchestration needs the command-line tools its instructions call (ssh, python and pip) and credentials named HF_TOKEN and WANDB_API_KEY. Our summary lists: SkyPilot installed with `pip install` and the cloud extras you need; Credentials for at least one cloud provider.

Does SkyPilot Multi-Cloud Orchestration access the network?

SKILL.md names 3 domains. As links in the text: github.com, docs.skypilot.co and slack.skypilot.co. This is read from the text; nothing was executed.

Is SkyPilot Multi-Cloud Orchestration safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does SkyPilot Multi-Cloud Orchestration use?

SkyPilot Multi-Cloud Orchestration is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does SkyPilot Multi-Cloud Orchestration use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.5k tokens, read only when the agent opens those files.

What are the alternatives to SkyPilot Multi-Cloud Orchestration?

Skills that share tags, products or a category with SkyPilot Multi-Cloud Orchestration: Resource Tagging (ancoleman/ai-design-components, 526 stars), Optimizing Costs (ancoleman/ai-design-components, 526 stars), Infrastructure Devops Cloud Architect (chendongqi/OPB-Skills, 125 stars) and Cloud Cost Optimization (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SkyPilot Multi-Cloud Orchestration?

Orchestra-Research (a GitHub organization) maintains it in Orchestra-Research/AI-Research-SKILLs, which has 13,374 GitHub stars. The repository holds 96 skills in this directory. The repository was last updated on June 16, 2026.

Source: Orchestra-Research/AI-Research-SKILLs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.