Coreweave Multi Env Setup

What it does

When your agent uses it

• Setting up multi-environment GPU infrastructure
• Separating namespaces
• Managing per-environment GPU quotas
• With phrases like coreweave environments

Example prompts

• “coreweave environments”
• “coreweave staging”
• “coreweave multi-env”
• “/coreweave-multi-env-setup”

Requirements

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

Workflow steps

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

1. 1Define overlays that differ only in reviewed capacity, endpoint, and namespace values.
2. 2Validate required variables and secret references before applying an overlay.
3. 3Promote dev to staging, run the service evaluation, then use a controlled production rollout.
4. 4Roll back the production overlay on an SLO, quality, or security-gate failure; do not copy staging credentials into production.

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:*)
  • Bash(kustomize:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • kubectl
  • curl

  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 these keys or tokens, usually read from environment variables:

  • CW_TOKEN

  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 Multi Env Setup loads about 1.4k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 354 words of instructions outside code blocks.

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

~87

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

~1.4k

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

• NoteMentions a .env fileSKILL.md:39

  d by a secrets manager, never committed `.env` files.

• NoteMentions a .env fileSKILL.md:69

  # Per-env files: .env.development, .env.staging, .env.production

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). 354 words, ~1,436 tokens.

name

coreweave-multi-env-setup

description

Configure CoreWeave across development, staging, and production environments. Use when setting up multi-environment GPU infrastructure, separating namespaces, or managing per-environment GPU quotas. Trigger with phrases like "coreweave environments", "coreweave staging", "coreweave multi-env", "coreweave namespace setup".

allowed-tools

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

const coreweaveConfig = (env: string) => ({
  development: {
    namespace: "app-dev", apiEndpoint: process.env.CW_API_ENDPOINT_DEV!,
    token: process.env.CW_TOKEN_DEV!, gpuType: "L40", scaleToZero: true, replicas: [0, 1],
  },
  staging: {
    namespace: "app-staging", apiEndpoint: process.env.CW_API_ENDPOINT_STG!,
    token: process.env.CW_TOKEN_STG!, gpuType: "A100_PCIE_40GB", scaleToZero: true, replicas: [0, 2],
  },
  production: {
    namespace: "app-prod", apiEndpoint: process.env.CW_API_ENDPOINT_PROD!,
    token: process.env.CW_TOKEN_PROD!, gpuType: "A100_PCIE_80GB", scaleToZero: false, replicas: [2, 10],
  },
}[env]);

# Per-env files: .env.development, .env.staging, .env.production
CW_API_ENDPOINT_{DEV|STG|PROD}=https://k8s.{ord1|ord1|las1}.coreweave.com
CW_TOKEN_{DEV|STG|PROD}=<service-account-token>
CW_NAMESPACE={app-dev|app-staging|app-prod}
CW_GPU_TYPE={L40|A100_PCIE_40GB|A100_PCIE_80GB}

function validateCoreWeaveEnv(env: string): void {
  const required = ["CW_API_ENDPOINT", "CW_TOKEN", "CW_NAMESPACE", "CW_GPU_TYPE"];
  const suffix = { development: "_DEV", staging: "_STG", production: "_PROD" }[env];
  const missing = required
    .map((k) => (k.includes("NAMESPACE") ? k : `${k}${suffix}`))
    .filter((k) => !process.env[k]);
  if (missing.length) throw new Error(`Missing env vars for ${env}: ${missing.join(", ")}`);
}

# 1. Validate model in dev namespace
kubectl -n app-dev get inferenceservice my-model -o jsonpath='{.status.conditions}'

# 2. Apply staging overlay with production GPU type
kustomize build k8s/overlays/staging | kubectl apply -f -

# 3. Run inference benchmarks against staging endpoint
curl -X POST https://staging.myapp.coreweave.cloud/v1/predict -d @test-payload.json

# 4. Promote to production (blue-green via namespace switch)
kustomize build k8s/overlays/prod | kubectl apply -f -
kubectl -n app-prod rollout status deployment/my-model

kustomize build k8s/overlays/staging | kubectl apply --dry-run=server -f -
kustomize build k8s/overlays/staging | kubectl apply -f -
kubectl -n app-staging rollout status deployment/my-model --timeout=10m

© 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-multi-env-setup of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287