Coreweave Upgrade Migration

What it does

When your agent uses it

• Migrating from A100 to H100
• Upgrading CUDA versions
• Updating inference server versions
• With phrases like upgrade coreweave

Example prompts

• “upgrade coreweave”
• “coreweave gpu migration”
• “coreweave cuda upgrade”
• “/coreweave-upgrade-migration”

Requirements

• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(kubectl:*), Grep

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Inventory current selectors, images, API versions, volumes, quotas, and service SLOs.
2. 2Update the manifest in staging, validate server-side, and run compatibility and performance checks.
3. 3Promote through a bounded canary only after the readiness, quality, latency, and integrity gates pass.
4. 4Use the prior immutable revision on any failed gate; do not delete old data or nodes until the observation period closes.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(kubectl:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • kubectl

  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):

  • docs.coreweave.com

  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.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Coreweave Upgrade Migration loads about 1.9k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 476 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~78

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

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

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 476 words, ~1,949 tokens.

name

coreweave-upgrade-migration

description

Upgrade CoreWeave deployments and migrate between GPU types. Use when migrating from A100 to H100, upgrading CUDA versions, or updating inference server versions. Trigger with phrases like "upgrade coreweave", "coreweave gpu migration", "coreweave cuda upgrade", "migrate coreweave".

allowed-tools

Read, Write, Edit, Bash(kubectl:*), Grep

compatibility

Designed for Claude Code

version

1.11.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, gpu-cloud, kubernetes, inference, coreweave

import { KubeConfig, CoreV1Api } from "@kubernetes/client-node";

async function detectCoreWeaveVersion(): Promise<void> {
  const kc = new KubeConfig();
  kc.loadFromDefault();
  const k8sApi = kc.makeApiClient(CoreV1Api);

  // Check current namespace GPU allocations
  const pods = await k8sApi.listNamespacedPod("my-namespace");
  for (const pod of pods.body.items) {
    const gpuClass = pod.spec?.nodeSelector?.["gpu.nvidia.com/class"];
    const cudaVersion = pod.metadata?.labels?.["cuda-version"];
    console.log(`Pod ${pod.metadata?.name}: GPU=${gpuClass}, CUDA=${cudaVersion}`);
  }

  // Detect deprecated instance types
  const deprecated = ["A100_PCIE_40GB", "V100_PCIE_16GB", "RTX_A5000"];
  const activeGpus = pods.body.items
    .map((p) => p.spec?.nodeSelector?.["gpu.nvidia.com/class"])
    .filter(Boolean);
  const stale = activeGpus.filter((g) => deprecated.includes(g!));
  if (stale.length > 0) console.warn(`Deprecated GPU types in use: ${stale.join(", ")}`);
}

// CoreWeave instance type labels changed in 2025 platform update
// Old: gpu.nvidia.com/class: "A100_PCIE_80GB"
// New: gpu.nvidia.com/class: "H100_SXM5_80GB"

interface DeploymentMigration {
  oldSelector: Record<string, string>;
  newSelector: Record<string, string>;
  cudaMinVersion: string;
}

const GPU_MIGRATIONS: DeploymentMigration[] = [
  {
    oldSelector: { "gpu.nvidia.com/class": "A100_PCIE_80GB" },
    newSelector: { "gpu.nvidia.com/class": "H100_SXM5_80GB" },
    cudaMinVersion: "12.4",
  },
  {
    oldSelector: { "gpu.nvidia.com/class": "A100_SXM4_80GB" },
    newSelector: { "gpu.nvidia.com/class": "H100_SXM5_80GB" },
    cudaMinVersion: "12.4",
  },
];

function migrateNodeSelector(manifest: any, migration: DeploymentMigration): any {
  const selector = manifest.spec?.template?.spec?.nodeSelector;
  if (!selector) return manifest;
  for (const [key, oldVal] of Object.entries(migration.oldSelector)) {
    if (selector[key] === oldVal) {
      selector[key] = migration.newSelector[key];
    }
  }
  return manifest;
}

import { AppsV1Api, KubeConfig } from "@kubernetes/client-node";

async function rollbackDeployment(namespace: string, name: string): Promise<void> {
  const kc = new KubeConfig();
  kc.loadFromDefault();
  const appsApi = kc.makeApiClient(AppsV1Api);

  // Kubernetes rollout undo — reverts to previous revision
  const deployment = await appsApi.readNamespacedDeployment(name, namespace);
  const currentRevision = deployment.body.metadata?.annotations?.["deployment.kubernetes.io/revision"];
  console.log(`Rolling back ${name} from revision ${currentRevision}`);

  // Patch to trigger rollback via revision annotation
  await appsApi.patchNamespacedDeployment(name, namespace, {
    spec: { template: { metadata: { annotations: { "kubectl.kubernetes.io/restartedAt": new Date().toISOString() } } } },
  }, undefined, undefined, undefined, undefined, undefined, { headers: { "Content-Type": "application/strategic-merge-patch+json" } });
  console.log(`Rollback initiated for ${name} in ${namespace}`);
}

kubectl -n inference-staging apply --dry-run=server -f migration.yaml
kubectl -n inference-staging apply -f migration.yaml
kubectl -n inference-staging rollout status deployment/inference --timeout=15m

© jeremylongshore, MIT. 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 skills/.curated/coreweave-upgrade-migration of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287