Coreweave Observability

What it does

When your agent uses it

• Implementing GPU metrics dashboards
• Configuring alerts
• Tracking inference latency and throughput
• With phrases like coreweave monitoring

Example prompts

• “coreweave monitoring”
• “coreweave observability”
• “coreweave gpu metrics”
• “/coreweave-observability”

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. 1Tag metrics with bounded values such as namespace, model family, and status; do
2. 2Build dashboards for utilization, memory, queue depth, latency, error rate, and
3. 3Route critical alerts to the responsible on-call team and link a runbook that
4. 4Test one alert in a non-production namespace and verify that the receipt contains

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):

  • 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 Observability loads about 1.4k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 404 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

~1.4k

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

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). 404 words, ~1,434 tokens.

name

coreweave-observability

description

Set up GPU monitoring and observability for CoreWeave workloads. Use when implementing GPU metrics dashboards, configuring alerts, or tracking inference latency and throughput. Trigger with phrases like "coreweave monitoring", "coreweave observability", "coreweave gpu metrics", "coreweave grafana".

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

async function trackInference(model: string, fn: () => Promise<any>) {
  const start = Date.now();
  try {
    const result = await fn();
    metrics.record('coreweave.inference.latency', Date.now() - start, { model, status: 'ok' });
    metrics.increment('coreweave.inference.completed', { model });
    return result;
  } catch (err) {
    metrics.increment('coreweave.inference.errors', { model, error: err.code });
    throw err;
  }
}

async function coreweaveHealth(): Promise<Record<string, string>> {
  const gpu = await queryPrometheus('avg(DCGM_FI_DEV_GPU_UTIL)');
  const mem = await queryPrometheus('avg(DCGM_FI_DEV_FB_USED/(DCGM_FI_DEV_FB_USED+DCGM_FI_DEV_FB_FREE))');
  const pods = await queryPrometheus('kube_deployment_status_replicas_available{namespace="inference"}');
  return {
    gpu_utilization: gpu > 20 ? 'healthy' : 'underutilized',
    gpu_memory: mem < 0.9 ? 'healthy' : 'critical',
    inference_pods: pods > 0 ? 'healthy' : 'down',
  };
}

const alerts = [
  { metric: 'DCGM_FI_DEV_GPU_UTIL', condition: 'avg < 20', window: '30m', severity: 'warning' },
  { metric: 'gpu_memory_pct', condition: '> 0.95', window: '5m', severity: 'critical' },
  { metric: 'inference_latency_p99', condition: '> 500ms', window: '10m', severity: 'warning' },
  { metric: 'pod_restart_count', condition: '> 3', window: '15m', severity: 'critical' },
];

function logGpuEvent(event: string, node: string, data: Record<string, any>) {
  console.log(JSON.stringify({
    service: 'coreweave', event, node,
    gpu_model: data.gpu_model, utilization: data.util,
    memory_pct: data.memPct, temperature: data.temp,
    timestamp: new Date().toISOString(),
  }));
}

kubectl -n inference-staging scale deployment/summarizer --replicas=0
kubectl -n inference-staging get pods --watch
# Confirm the unavailable-replica alert reaches the test route, then restore it.
kubectl -n inference-staging scale deployment/summarizer --replicas=1

© 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-observability of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287