gke-custom-golden-image-discovery — Claude Code skill
This skill finds a golden base image for a custom GKE node from the cluster version, OS, architecture, accelerator, and security requirements.
npx skills add google/skills --skill gke-custom-golden-image-discovery -a claude-codeWhat gke-custom-golden-image-discovery does
The skill maps a GKE configuration to the golden base image used to create a custom node image. It checks the GKE version, operating system, architecture, accelerators, gVisor, signed modules, cgroup mode, and TPU settings. When the request leaves some fields unclear, it applies the defaults from its discovery rules.
Its workflow extracts the configuration, derives the major/minor version, fetches the base-image map, and filters entries for an exact match. Before running gcloud, REST API, or MCP commands, the skill requires reading references/attribution.md; terminal gcloud commands also need the specified request attribution.
Install it when you need the base image for a custom GKE node. Use another skill for general GKE cluster creation or standard node pool management.
What it helps with
- find a golden base image for a custom GKE node
- map a GKE version to the matching image name
- match COS or Ubuntu with the node architecture
- select an image for GPU, TPU, or other accelerators
- check gVisor and cgroup settings
Example prompts for the agent
- Find the golden base image for GKE 1.34.1-gke.2909000 using COS and X86_64.
- Select a custom GKE node image for an H100 with gVisor enabled.
- Match this GKE configuration against the base-image map.
How to install gke-custom-golden-image-discovery
1Skills CLI (Vercel)
npx skills add google/skills --skill gke-custom-golden-image-discovery -a claude-code2Manually: put the files in place
~/.claude/skills/gke-custom-golden-image-discovery/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gke-custom-golden-image-discovery/
1Skills CLI (Vercel)
npx skills add google/skills --skill gke-custom-golden-image-discovery -a codex2Manually: put the files in place
.agents/skills/gke-custom-golden-image-discovery/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/gke-custom-golden-image-discovery/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install google/skills gke-custom-golden-image-discovery2Manually: put the files in place
.github/skills/gke-custom-golden-image-discovery/SKILL.md1Skills CLI (Vercel)
npx skills add google/skills --skill gke-custom-golden-image-discovery -a gemini-cli2Platform CLI
gemini skills install https://github.com/google/skills --path skills/cloud/gke-custom-golden-image-discoveryManually: put the files in place
.devin/skills/gke-custom-golden-image-discovery/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set172
The whole set →Similar
Questions about gke-custom-golden-image-discovery
How do I install gke-custom-golden-image-discovery in Claude Code?
Run npx skills add google/skills --skill gke-custom-golden-image-discovery -a claude-code. The skill file is placed at ~/.claude/skills/gke-custom-golden-image-discovery/SKILL.md.
What does gke-custom-golden-image-discovery do?
It finds the golden base image for a custom GKE node. The skill maps cluster parameters to an image name from the GKE base-image map.
Which GKE settings does the skill use?
It matches the GKE version, OS, architecture, accelerators, gVisor, signed modules, cgroup mode, and TPU settings. Its discovery rules provide defaults for unspecified choices.
Source text
SKILL.md · Apache-2.0
---
name: gke-custom-golden-image-discovery
metadata:
version: "1.0.1"
category: Containers
description: >-
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).
---
# 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](references/attribution.md). 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
1. **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.
2. **Determine Minor Version**: Extract the major/minor version (e.g., `1.34`).
3. **Fetch Data**: `curl` the mapping: `https://www.gstatic.com/gke-image-maps/base-images/node-config-to-base-images-<MINOR_VERSION>.json`
4. **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.
5. **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.
6. **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`"
© google · Apache-2.0 · google/skills