Gke Custom Golden Image Discovery — Agent Skill by Google

From the author

Discovers golden base images for creating GKE custom node images based on technical specifications or context clues. Use when finding the golden base image for custom GKE node creation, mapping cluster configuration parameters (GKE version, OS, architecture, accelerators, gVisor, cgroups) to image names, or querying GKE base image maps. Don't use for general GKE cluster creation (use gke-cluster-creation) or standard node pool management (use gke-basics).

— the description by Google

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill assists users in identifying the appropriate golden base image required for building custom GKE node images. It bridges the gap between high-level user requirements and specific technical image identifiers by parsing configuration parameters such as GKE version, OS, architecture, and hardware acceleration needs. The skill follows a structured discovery workflow, including data retrieval from official GKE image maps and logical filtering to ensure compatibility with the user's cluster setup.

What it does

Maps high-level cluster requirements to specific GKE golden base image names.
Infers technical configuration values from natural language descriptions.
Retrieves and parses official GKE base image mapping data.
Validates GKE version compatibility for custom node image creation.
Provides guidance on adjusting configuration parameters like cgroup modes or sandboxing to find valid image matches.

When to use it

When you need to identify the base image for a custom GKE node pool.
When you have a specific GKE version and need to map it to a compatible OS and architecture.
When configuring nodes with specialized hardware like GPUs or TPUs.
When you need to determine if a specific combination of gVisor, cgroups, and security settings is supported.

Advantages

Reduces manual lookup time for complex GKE image versioning.
Ensures technical accuracy by using official GKE image mapping data.
Simplifies the selection process by providing sensible defaults for missing configuration details.
Helps troubleshoot configuration mismatches by suggesting alternative parameter settings.

Usage examples

“I need a golden image for GKE 1.34.1-gke.2909000 using Ubuntu on ARM64.”: The agent retrieves the mapping file for version 1.34, filters for Ubuntu and ARM64, and returns the specific golden base image string.
“Find me a base image for a hardened GKE 1.34 cluster with Nvidia GPUs.”: The agent infers the need for accelerators and signed modules, then queries the image map to provide the correct image identifier for that hardware and security configuration.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/google/gke-custom-golden-image-discovery/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip gke-custom-golden-image-discovery.zip -d .agents/skills

Documentation by Google

GKE Golden Base Image Discovery Expert

You are an expert at helping users find the correct "golden" base image for creating custom GKE images. You can bridge the gap between a user's high-level description and the technical JSON requirements.

Attribution

MUST READ: Before executing any gcloud, REST API, or MCP command, you MUST read Usage Attribution. For commands executed directly in the terminal (never in generated scripts, Terraform, or user code), prefix gcloud with CLOUDSDK_METRICS_REQUEST_ATTRIBUTION="agent-skills/1.0 (skill:gke-custom-golden-image-discovery)" and append agent-skills/1.0 (skill:gke-custom-golden-image-discovery) to User-Agent headers.

Information Gathering & Inference

If a user doesn't know their exact configuration, use the following Context Clues and Sensible Defaults to infer the values:

Field	Context Clues	Default Value
GKE Version	(Required) Must be 1.34.1-gke.2909000 or later.	N/A
Operating System	"I like Google's OS" -> COS; "I need Ubuntu/standard Linux" -> Ubuntu.	COS
Architecture	"Using ARM/Ampere" -> ARM64; "Standard/Intel/AMD" -> X86_64.	X86_64
gVisor Enabled	"Need a sandbox" or "gVisor" mentioned -> true.	false
Has Accelerators	Mention of "GPU", "accelerator", "Nvidia", "TPU", or any specific hardware models (e.g., T4, A100, H100, L4) -> true.	false
Enforce Signed Modules	"Hardened nodes" or "Signed modules" mentioned -> true.	false
Cgroup Mode	Almost all GKE 1.26+ clusters use V2. Only V1 if explicitly legacy.	CGROUP_MODE_V2
TPU	Mention of "TPU" -> true.	false

Discovery Workflow

Extract Info: Parse the user's request for the GKE Version and any context clues for the fields above. Be proactive: if a user mentions any specialized hardware or security requirements, map them to the corresponding technical flags.
Determine Minor Version: Extract the major/minor version (e.g., 1.34).
Fetch Data: curl the mapping: https://www.gstatic.com/gke-image-maps/base-images/node-config-to-base-images-<MINOR_VERSION>.json
Filter Logic:
- Match version exactly.
- Match node_info using the inferred or provided values:
  - image_family: COS_CONTAINERD (COS) or UBUNTU_CONTAINERD (Ubuntu).
  - Other fields match exactly.
Refine Search: If no exact match is found with defaults, try toggling cgroup_mode to CGROUP_MODE_V1 or gvisor_enabled to false and inform the user.
Warns about invalid input: If the inputted GKE version is invalid, inform the user that the version is unsupported.

Example Output

"Based on your setup (GKE 1.34.1-gke.2909000, COS, and using the new H100 GPUs), I've inferred you need the X86_64 image with Accelerators enabled. The golden base image is: gke-1341-gke2909000-cos-125-19216-0-115-c-nvda"

Files

ATTRIBUTION.mdAdded by AutoGineer884 B
LICENSELicence file added by AutoGineer11.1 KiB
SKILL.md4.3 KiB
references/attribution.md1.9 KiB

references/attribution.md

Usage Attribution

MUST READ: Before executing any gcloud, REST API, or MCP command with this skill, follow these usage attribution instructions. Tag every command you execute directly in the terminal so usage can be attributed. The tag identifies only the skill and its version; it carries no user data.

gcloud CLI Commands: Prefix every gcloud invocation, whatever the subcommand, with the metrics environment variable. Set it inline on each command because shell state may not persist between commands:
```
CLOUDSDK_METRICS_REQUEST_ATTRIBUTION="agent-skills/1.0 (skill:gke-custom-golden-image-discovery)" \
gcloud <command> [flags]
```
Do not use gcloud config set for this: it would persist beyond the current task and mislabel unrelated usage.
Direct HTTP, REST, and MCP Requests: On direct HTTP calls to Google Cloud APIs (for example with curl) or HTTP requests to a remote MCP server, include agent-skills/1.0 (skill:gke-custom-golden-image-discovery) in the User-Agent header. If a User-Agent header is already specified, append this string to the end of it rather than overwriting existing User-Agent data — the collection pipeline parses the agent-skills/<version> and skill:<name> tokens, so any rewording breaks attribution:
```
User-Agent: <existing_user_agent> agent-skills/1.0 (skill:gke-custom-golden-image-discovery)
```
Constraint for Generated Code: The tracking prefix is strictly for commands you execute directly in the terminal. Do NOT include this tracking prefix in generated scripts, Terraform templates, or code provided to the user for their own repositories.
User Opt-Out: If the user asks to disable or remove tracking or attribution tags, omit the CLOUDSDK_METRICS_REQUEST_ATTRIBUTION variable and custom User-Agent suffix from all commands.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs network access, Needs Node.js

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

K8s Manifest Generator
Seth Hobson· Community
A structured guide for generating secure, production-ready Kubernetes manifests including Deployments, Services, ConfigMaps, and Secrets.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository42.3k
Cloud Infrastructure Kubernetes Architect
Seth Hobson· Community
An expert Kubernetes architect specializing in cloud-native infrastructure, GitOps workflows, and container orchestration.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k
Service Mesh Expert
Seth Hobson· Community
An expert architect for designing, securing, and managing service mesh deployments in cloud-native environments.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k
Istio Traffic Management
Seth Hobson· Community
A comprehensive guide to managing service mesh traffic, routing, and resilience policies using Istio.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Kubernetes Operations Kubernetes Architect
Seth Hobson· Community
An expert Kubernetes architect providing guidance on cloud-native infrastructure, GitOps workflows, and container orchestration.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k
Cicd Automation Kubernetes Architect
Seth Hobson· Community
An expert Kubernetes architect providing guidance on cloud-native infrastructure, GitOps workflows, and container orchestration.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download gke-custom-golden-image-discovery.zip