Evidence record · captured 2026-10-11

GKE Kubernetes Manifests

Makes the agent generate or update Kubernetes YAML for GKE Autopilot and Standard under strict rules: explicit namespaces, security contexts, CPU/memory requests and limits, readiness/liveness/startup probes, secret and volume mounts, Gateway API routes, network policies and Spot VM targeting. References cover basic workloads, AI inference, Gateway API and network policy.

Official publisherUnverifiedSource reviewedBehavior not tested

Source review

Editorial assessment

This is a source-only assessment. It does not claim runtime or security testing.

What it does

Makes the agent apply a fixed hardening and cost profile to GKE YAML: explicit namespaces, dedicated ServiceAccounts, non-root read-only containers, mandatory probes, and Autopilot-aware requests and limits.

Best for

Generating Deployment, Service and PodDisruptionBudget manifests for GKE Autopilot or Standard
Writing model-serving manifests with GPU requests, /dev/shm and GCS FUSE mounts
Exposing a service through Gateway API HTTPRoutes instead of Ingress

Strengths in the source

Explains that Autopilot bills on requests and raises requests to match limits, so it sets them equal there.
Requires both liveness and readiness probes, plus a startupProbe for slow-starting apps such as LLM servers.
Warns that renaming a list item's name key under server-side apply leaves the old entry orphaned.
References include a hardened Nginx workload, default-deny network policy, an inference workload and Gateway API routing.

Limitations

Automatically targets Spot VMs for namespaces containing -dev, -test or -staging, which changes scheduling unless the user overrides it.
Expects a SETTINGS.md and Google developer-knowledge query tools that are not part of the skill folder.
For inference it requires gcloud container ai profiles manifests create, which needs Google Cloud SDK access.

When not to use it

Live cluster operations or pod troubleshooting, which the skill routes to other GKE skills.
Kubernetes clusters outside GKE, where its storage classes, Spot labels and Gateway classes do not apply.

Reviewed by Retenta editorial on 2026-10-11; scope: source only.

Files included in this review

skills/cloud/gke-manifest-generation/SKILL.md

Evidence and boundaries

Execution · not tested

Retenta has not executed this skill.

Security · not tested

The skill folder bundles no executable scripts. Retenta has not run a security scan.

Pinned publisher source: skills/cloud/gke-manifest-generation/SKILL.md
Revision: 4b940dd4b5f5759794cc257266cb8cb7524b7a66
License evidence: Apache-2.0Retenta preserves the license text captured with this immutable upstream snapshot; no independent legal or security review is claimed.
Last source change: 2026-09-21
Independent verification: Published by Google, but not independently verified by a third-party reviewer.
Upstream repository: Open publisher repository

Compatibility

Claude Code

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

OpenAI Codex

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

Antigravity

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

any Agent Skills client via npx skills

documented

Named in the upstream skill or repository documentation; not tested by Retenta.

Requirements and access

kubectl / gcloud (for applying and verifying)
GKE cluster access

Referenced tools

No named tool is required by the reviewed SKILL.md.

Install from the source

Clones the current default branch, which may be newer than the reviewed revision 4b940dd. The destination shown is Claude Code's personal skills folder; other agents read the same folder from their own skills directory.

View the SKILL.md at its source Verify the publisher's install documentation

More DevOps skills →

Install the full skill folder

git clone --depth 1 https://github.com/google/skills.git
cp -R skills/skills/cloud/gke-manifest-generation ~/.claude/skills/gke-manifest-generation

Thyme RAG Capsules

Make this skill’s state durable, governed, and portable.

A Retenta capsule lets agents recall prior work, append provenance-stamped progress, and carry the memory to the next run.

Create durable agent memory Understand the evidence labels