Coreweave Data Handling

What it does

When your agent uses it

• Managing large datasets
• Configuring storage classes
• Implementing data pipelines for GPU workloads
• With phrases like coreweave data

Example prompts

• “coreweave data”
• “coreweave storage”
• “coreweave pvc”
• “/coreweave-data-handling”

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. 1Create or select an encrypted PVC in the approved region and grant its mount only
2. 2Import artifacts using a short-lived job; verify the expected SHA-256 before any
3. 3Export only to a reviewed destination, preserve the checksum and data-owner
4. 4Record storage provisioning, access changes, deletion, and external egress in the

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):

  • kubernetes.io

  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 Data Handling loads about 1.8k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 514 words of instructions outside code blocks.

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

~81

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

~1.8k

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). 514 words, ~1,799 tokens.

name

coreweave-data-handling

description

Handle training data and model artifacts on CoreWeave persistent storage. Use when managing large datasets, configuring storage classes, or implementing data pipelines for GPU workloads. Trigger with phrases like "coreweave data", "coreweave storage", "coreweave pvc", "coreweave dataset management".

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, BatchV1Api } from '@kubernetes/client-node';

async function importDataset(pvcName: string, sourceUrl: string, namespace: string) {
  const kc = new KubeConfig();
  kc.loadFromDefault();
  const batch = kc.makeApiClient(BatchV1Api);
  const job = {
    metadata: { name: `import-${Date.now()}`, namespace },
    spec: { template: { spec: {
      restartPolicy: 'Never',
      containers: [{ name: 'loader', image: 'python:3.11-slim',
        command: ['python3', '-c', `
import urllib.request, hashlib
dest = '/data/dataset.tar.gz'
urllib.request.urlretrieve('${sourceUrl}', dest)
print(f"SHA256: {hashlib.sha256(open(dest,'rb').read()).hexdigest()}")`],
        volumeMounts: [{ name: 'storage', mountPath: '/data' }],
      }],
      volumes: [{ name: 'storage', persistentVolumeClaim: { claimName: pvcName } }],
    }}}
  };
  await batch.createNamespacedJob(namespace, { body: job });
}

async function exportCheckpoint(pvcName: string, destBucket: string, ns: string) {
  // Validate export destination is in approved region list
  const APPROVED_REGIONS = ['us-east-1', 'us-central-1', 'eu-west-1'];
  const region = destBucket.split('-').slice(0, 3).join('-');
  if (!APPROVED_REGIONS.some(r => destBucket.includes(r))) {
    throw new Error(`Export blocked: ${region} not in approved regions`);
  }
  // Stream from PVC → object storage with integrity check
  const exportCmd = `tar czf - /models | gsutil cp - gs://${destBucket}/export.tar.gz`;
  console.log(`Exporting from PVC ${pvcName} to ${destBucket}`);
  return exportCmd;
}

interface ModelArtifact {
  name: string; format: 'safetensors' | 'gguf' | 'bin' | 'pt';
  sizeBytes: number; sha256: string;
}

function validateArtifact(artifact: ModelArtifact): string[] {
  const errors: string[] = [];
  if (!artifact.name || artifact.name.length > 255) errors.push('Invalid artifact name');
  if (artifact.sizeBytes <= 0) errors.push('Size must be positive');
  if (!/^[a-f0-9]{64}$/.test(artifact.sha256)) errors.push('Invalid SHA-256 hash');
  if (!['safetensors', 'gguf', 'bin', 'pt'].includes(artifact.format)) errors.push(`Unsupported format`);
  return errors;
}

kubectl -n research apply -f dataset-import-job.yaml
kubectl -n research wait --for=condition=complete job/dataset-import --timeout=30m
kubectl -n research logs job/dataset-import | grep SHA256

© 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-data-handling of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287