Coreweave CI Integration

What it does

When your agent uses it

• Automating container builds
• Deploying inference services from CI
• Validating GPU manifests in pull requests
• With phrases like coreweave CI

Example prompts

• “coreweave CI”
• “coreweave github actions”
• “coreweave pipeline”
• “/coreweave-ci-integration”

Requirements

• Docker
• A credential in GHCR_TOKEN
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(gh:*)

Workflow steps

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

1. 1Run deterministic unit and manifest validation on every pull request without credentials.
2. 2Run live integration checks only after merge or from an approved protected workflow.
3. 3Bound test resources, collect redacted pod events on failure, and revoke the staging identity if exposure is suspected.
4. 4Keep deploy approval and production rollout separate from the test job.

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(gh:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • gh
  • npm
  • 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.github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • GHCR_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 CI Integration loads about 1.6k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 352 words of instructions outside code blocks.

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

~85

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

~1.6k

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). 352 words, ~1,587 tokens.

name

coreweave-ci-integration

description

Integrate CoreWeave deployments into CI/CD pipelines with GitHub Actions. Use when automating container builds, deploying inference services from CI, or validating GPU manifests in pull requests. Trigger with phrases like "coreweave CI", "coreweave github actions", "coreweave pipeline", "automate coreweave deploy".

allowed-tools

Read, Write, Edit, Bash(gh:*)

compatibility

Designed for Claude Code

version

1.11.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, gpu-cloud, kubernetes, inference, coreweave

# .github/workflows/coreweave-ci.yml
name: CoreWeave CI
on:
  pull_request:
    paths: ['src/**', 'k8s/**', 'Dockerfile']
  push:
    branches: [main]

jobs:
  unit-tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with: { node-version: '20' }
      - run: npm ci
      - run: npm test -- --reporter=verbose

  deploy:
    if: github.ref == 'refs/heads/main'
    needs: unit-tests
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Build and push container
        run: |
          echo "${{ secrets.GHCR_TOKEN }}" | docker login ghcr.io -u ${{ github.actor }} --password-stdin
          docker build -t ghcr.io/${{ github.repository }}/inference:${{ github.sha }} .
          docker push ghcr.io/${{ github.repository }}/inference:${{ github.sha }}
      - name: Deploy to CoreWeave
        env:
          KUBECONFIG_DATA: ${{ secrets.COREWEAVE_KUBECONFIG }}
        run: |
          echo "$KUBECONFIG_DATA" | base64 -d > /tmp/kubeconfig
          export KUBECONFIG=/tmp/kubeconfig
          kubectl set image deployment/inference \
            inference=ghcr.io/${{ github.repository }}/inference:${{ github.sha }}
          kubectl rollout status deployment/inference --timeout=300s

// tests/coreweave-service.test.ts
import { describe, it, expect, vi } from 'vitest';
import { deployInferenceModel } from '../src/coreweave-service';

vi.mock('@kubernetes/client-node', () => ({
  KubeConfig: vi.fn().mockImplementation(() => ({
    loadFromDefault: vi.fn(),
    makeApiClient: vi.fn().mockReturnValue({
      patchNamespacedDeployment: vi.fn().mockResolvedValue({ body: { status: { readyReplicas: 1 } } }),
      listNamespacedPod: vi.fn().mockResolvedValue({
        body: { items: [{ metadata: { name: 'inference-abc' }, status: { phase: 'Running' } }] },
      }),
    }),
  })),
  AppsV1Api: vi.fn(),
}));

describe('CoreWeave Service', () => {
  it('deploys inference model with GPU requests', async () => {
    const result = await deployInferenceModel('llama-70b', { gpu: 'A100', count: 4 });
    expect(result.status).toBe('deployed');
    expect(result.gpuType).toBe('A100');
  });
});

// tests/integration/coreweave.integration.test.ts
import { describe, it, expect } from 'vitest';
import { KubeConfig, CoreV1Api } from '@kubernetes/client-node';

const hasKubeconfig = !!process.env.COREWEAVE_KUBECONFIG;

describe.skipIf(!hasKubeconfig)('CoreWeave Live API', () => {
  it('lists GPU nodes in namespace', async () => {
    const kc = new KubeConfig();
    kc.loadFromString(Buffer.from(process.env.COREWEAVE_KUBECONFIG!, 'base64').toString());
    const k8sApi = kc.makeApiClient(CoreV1Api);
    const { body } = await k8sApi.listNamespacedPod('default');
    expect(Array.isArray(body.items)).toBe(true);
  });
});

npm test
gh workflow run coreweave-integration.yml --ref main

© 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-ci-integration of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287