New: 97,000+ 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

Deploy Controller

by ai-runway in ai-runway/airunway

Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster

Apache-2.0Auto-check passedDevOps & Cloud

Install Deploy Controller

skills CLI
$ npx skills add ai-runway/airunway --skill deploy-controller -a claude-code

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

GitHub CLI
$ gh skill install ai-runway/airunway deploy-controller --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/ai-runway/airunway.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deploy-controller .claude/skills/deploy-controller && 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
deploy-controller
GitHub stars
101
Token cost
~927 tokens
SKILL.md length
282 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster

  • Works in 7 steps: Safety check → Gather inputs → Resolve image names → …
  • Tasks that involve Deployment
  • SKILL.md covers Step 0 — Safety check, Step 1 — Gather inputs, Step 2 — Resolve image names and Step 3 — Build image, plus 3 more sections
  • Calls make and kubectl

What it does

Deploy Controller is an agent skill from ai-runway/airunway. Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Deployment and Container orchestration. It works with NVIDIA AI Platform, vLLM, Kubernetes and Linux. The repository describes itself as: ✈️ Kubernetes-native platform for deploying and managing AI inference across multiple providers. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Deployment
  • Tasks that involve Container orchestration

Example prompts

  • “/deploy-controller”

Requirements

  • Docker

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Safety check
  2. Gather inputs
  3. Resolve image names
  4. Build image
  5. Deploy manifests to cluster
  6. Rollout restart (only if deployment exists)
  7. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 5b8511b. 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:

    • make
    • kubectl

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

  • Network

    No URLs in SKILL.md. Its commands use kubectl, which can reach the network depending on how they are called.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Deploy Controller loads about 927 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 282 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~927

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 ai-runway/airunway at commit 5b8511b, republished under its Apache-2.0 licence (© ai-runway). 282 words, ~927 tokens.

Download SKILL.mdSave it as .claude/skills/deploy-controller/SKILL.md (or your agent's skills folder).
name
deploy-controller
description
Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster
argument-hint
[component] [registry] [push|load] [platform]

Build and redeploy an airunway component to the cluster.

⚠️ Security: This skill performs destructive cluster operations. All steps require explicit human confirmation. Never run against production clusters. Verify the target cluster context before proceeding.

Step 0 — Safety check

Before anything else, run:

bash
kubectl config current-context

Show the output and ask: "You are targeting cluster <context>. This skill will build, push, and deploy images. Is this a dev/test cluster? Proceed? (yes/no)"

Do not proceed without explicit "yes".

Step 1 — Gather inputs

Parse $ARGUMENTS positionally: [component] [registry] [push|load] [platform]

Ask only for values not already provided by $ARGUMENTS.

Question 1 — Which component?

Which component do you want to deploy?
  1. controller
  2. provider: dynamo
  3. provider: kaito
  4. provider: kuberay
  5. provider: llmd

Question 2 — Container registry prefix? "What container registry/username prefix should be used? (e.g. myregistry, ghcr.io/myorg)"

Question 3 — Push or load? "Should the image be pushed to the remote registry or loaded into the local cluster?"

  1. push  — PUSH=true  (publishes to remote registry)
  2. load  — PUSH=false (loads into local cluster via docker buildx --load)

Question 4 — Target platform? "What platform(s) should the image be built for? (default: linux/amd64)" Common values: linux/amd64, linux/arm64, linux/amd64,linux/arm64

Confirm before proceeding: "Ready to build <image> for <platform> with PUSH=<true|false>. Proceed? (yes/no)"

Step 2 — Resolve image names

ComponentImage name patternDeployment name (airunway-system)
controller<registry>/airunway-controller:latestairunway-controller-manager
dynamo<registry>/airunway-dynamo-provider:latestairunway-dynamo-provider
kaito<registry>/airunway-kaito-provider:latest(no separate deployment — skip rollout)
kuberay<registry>/airunway-kuberay-provider:latest(no separate deployment — skip rollout)
llmd<registry>/airunway-llmd-provider:latestairunway-llmd-provider

Step 3 — Build image

Run sequentially. Stop and report the full error output if any step fails.

If component = controller:

bash
make controller-docker-build CONTROLLER_IMG=<image> PUSH=<true|false> PLATFORM=<platform>

If component = dynamo | kaito | kuberay | llmd:

bash
cd providers/<component>
make docker-build IMG=<image> PUSH=<true|false> PLATFORM=<platform>
cd ../..

Step 4 — Deploy manifests to cluster

If component = controller:

bash
make controller-deploy CONTROLLER_IMG=<image>

If component = dynamo | kaito | kuberay | llmd:

bash
cd providers/<component>
make deploy IMG=<image>
cd ../..

Step 5 — Rollout restart (only if deployment exists)

If the component has a known deployment name (see table above):

bash
kubectl rollout restart deployment <deployment-name> -n airunway-system
kubectl rollout status deployment <deployment-name> -n airunway-system

Step 6 — Report

Summarize:

  • Component and image deployed
  • Platform and PUSH value used
  • Whether the rollout completed successfully
  • Any warnings or errors encountered

© ai-runway, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/deploy-controller of ai-runway/airunway.

Open the folder on GitHubat commit 5b8511b

Compare with similar skills

Deploy Controller 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.

Deploy Controller compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deploy Controller this skillai-runway/airunway101—~927Automated safety check: PassApache-2.0
Openbkn Deployopenbkn-ai/bkn-foundry629—~1.9kAutomated safety check: NotesCustom licence
K8s Manifest GeneratorCybereason-Public/owLSM28011 repos~433Automated safety check: PassGPL-2.0
Azure Diagnosticsmicrosoft/GitHub-Copilot-for-Azure2551 repos~1.6kAutomated safety check: PassMIT
Model Serving Kubernetessickn33/agentic-awesome-skills47k1 repos~2.3kAutomated safety check: PassMIT
Gke Manifest Generationgoogle/skills21k—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Openbkn Deploy

    openbkn-ai/bkn-foundry

    Deploy or upgrade OpenBKN on a customer-authorized Linux server through the repository's deploy scripts, with preflight checks, explicit confirmation, secret handling, and post-deployment…

    629 GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • K8s Manifest Generator

    Cybereason-Public/owLSM

    Step-by-step guidance for creating production-ready Kubernetes manifests including Deployments, Services, ConfigMaps, Secrets, and PersistentVolumeClaims.

    280 GitHub starsUsed in 11 repos~433 tokens
    DevOps & CloudAuto-check passed

  • Azure Diagnostics

    microsoft/GitHub-Copilot-for-Azure

    Official

    Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage.

    255 GitHub starsUsed in 1 repo~1.6k tokens
    DevOps & CloudAuto-check passed

  • Model Serving Kubernetes

    sickn33/agentic-awesome-skills

    Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server.

    47k GitHub starsUsed in 1 repo~2.3k tokens
    DevOps & CloudAuto-check passed

  • Gke Manifest Generation

    google/skills

    Official

    Generates and updates secure, production-ready Kubernetes YAML manifests optimized for GKE Autopilot and GKE Standard clusters.

    21k GitHub stars~3.1k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Dynamo Recipe Runner

    NVIDIA/skills

    Official

    Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes.

    3.5k GitHub stars~1.8k tokensUpdated today
    DevOps & CloudAuto-check passed

Works with

Categories

Questions about Deploy Controller

What does Deploy Controller do?

Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster. Deploy Controller is an agent skill from ai-runway/airunway.

When should I use Deploy Controller?

Deploy Controller fits situations like: tasks that involve Deployment; tasks that involve Container orchestration.

How do I install Deploy Controller in Claude Code?

Run `npx skills add ai-runway/airunway --skill deploy-controller -a claude-code`. Or copy the skill folder (.agents/skills/deploy-controller in ai-runway/airunway) into .claude/skills/deploy-controller in your project. Claude Code loads it when a task matches its description.

How do I install Deploy Controller in Codex?

Run `npx skills add ai-runway/airunway --skill deploy-controller -a codex`. Or copy the skill folder (.agents/skills/deploy-controller in ai-runway/airunway) into .agents/skills/deploy-controller in your project. Codex loads it when a task matches its description.

Can I use Deploy Controller 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 ai-runway/airunway --skill deploy-controller -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deploy-controller, .gemini/skills/deploy-controller, .github/skills/deploy-controller and .opencode/skills/deploy-controller in your project.

What does Deploy Controller need to run?

Going by SKILL.md and its folder, Deploy Controller needs the command-line tools its instructions call (make and kubectl). Our summary lists: Docker.

Does Deploy Controller access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deploy Controller 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 Deploy Controller use?

Deploy Controller is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deploy Controller use?

About 927 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deploy Controller?

Skills that share tags, products or a category with Deploy Controller: Openbkn Deploy (openbkn-ai/bkn-foundry, 629 stars), K8s Manifest Generator (Cybereason-Public/owLSM, 280 stars), Azure Diagnostics (microsoft/GitHub-Copilot-for-Azure, 255 stars) and Model Serving Kubernetes (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deploy Controller?

ai-runway (a GitHub organization) maintains it in ai-runway/airunway, which has 101 GitHub stars. The repository was last updated on September 27, 2026.

Source: ai-runway/airunway on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.