coreweave-observability
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".
Best use case
coreweave-observability is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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".
Teams using coreweave-observability should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/coreweave-observability/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How coreweave-observability Compares
| Feature / Agent | coreweave-observability | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# CoreWeave Observability
## Overview
CoreWeave runs GPU-intensive workloads on Kubernetes where hardware failures, memory exhaustion, and underutilization directly impact cost and reliability. Observability must cover DCGM GPU metrics, Kubernetes pod health, inference latency, and job completion rates. Proactive monitoring prevents wasted spend on idle GPUs and catches OOM conditions before they cascade.
## Key Metrics
| Metric | Type | Target | Alert Threshold |
|--------|------|--------|-----------------|
| GPU utilization | Gauge | > 60% | < 20% for 30m |
| GPU memory usage | Gauge | < 85% | > 95% for 5m |
| Inference latency p99 | Histogram | < 200ms | > 500ms |
| Job completion rate | Counter | > 99% | < 95% per hour |
| Pod restart count | Counter | 0 | > 3 in 15m |
| Node GPU temperature | Gauge | < 80C | > 85C for 10m |
## Instrumentation
```typescript
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;
}
}
```
## Health Check Dashboard
```typescript
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',
};
}
```
## Alerting Rules
```typescript
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' },
];
```
## Structured Logging
```typescript
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(),
}));
}
```
## Error Handling
| Signal | Meaning | Action |
|--------|---------|--------|
| GPU util < 20% sustained | Idle GPUs burning cost | Scale down or reassign workload |
| GPU memory > 95% | OOM imminent | Reduce batch size or add nodes |
| Pod CrashLoopBackOff | Driver or config failure | Check DCGM logs, restart node |
| Inference latency spike | Contention or throttling | Review GPU temp and queue depth |
| Node NotReady | Hardware or network issue | Cordon node, migrate pods |
## Resources
- [CoreWeave Observability](https://www.coreweave.com/observability)
## Next Steps
For incident response, see `coreweave-incident-runbook`.Related Skills
windsurf-observability
Monitor Windsurf AI adoption, feature usage, and team productivity metrics. Use when tracking AI feature usage, measuring ROI, setting up dashboards, or analyzing Cascade effectiveness across your team. Trigger with phrases like "windsurf monitoring", "windsurf metrics", "windsurf analytics", "windsurf usage", "windsurf adoption".
webflow-observability
Set up observability for Webflow integrations — Prometheus metrics for API calls, OpenTelemetry tracing, structured logging with pino, Grafana dashboards, and alerting for rate limits, errors, and latency. Trigger with phrases like "webflow monitoring", "webflow metrics", "webflow observability", "monitor webflow", "webflow alerts", "webflow tracing".
vercel-observability
Set up Vercel observability with runtime logs, analytics, log drains, and OpenTelemetry tracing. Use when implementing monitoring for Vercel deployments, setting up log drains, or configuring alerting for function errors and performance. Trigger with phrases like "vercel monitoring", "vercel metrics", "vercel observability", "vercel logs", "vercel alerts", "vercel tracing".
veeva-observability
Veeva Vault observability for enterprise operations. Use when implementing advanced Veeva Vault patterns. Trigger: "veeva observability".
vastai-observability
Monitor Vast.ai GPU instance health, utilization, and costs. Use when setting up monitoring dashboards, configuring alerts, or tracking GPU utilization and spending. Trigger with phrases like "vastai monitoring", "vastai metrics", "vastai observability", "monitor vastai", "vastai alerts".
twinmind-observability
Monitor TwinMind transcription quality, meeting coverage, action item extraction rates, and memory vault health. Use when implementing observability, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind observability", "twinmind observability".
speak-observability
Monitor Speak API health, assessment latency, session metrics, and pronunciation score distributions. Use when implementing observability, or managing Speak language learning platform operations. Trigger with phrases like "speak observability", "speak observability".
snowflake-observability
Set up Snowflake observability using ACCOUNT_USAGE views, alerts, and external monitoring. Use when implementing Snowflake monitoring dashboards, setting up query performance tracking, or configuring alerting for warehouse and pipeline health. Trigger with phrases like "snowflake monitoring", "snowflake metrics", "snowflake observability", "snowflake dashboard", "snowflake alerts".
shopify-observability
Set up observability for Shopify app integrations with query cost tracking, rate limit monitoring, webhook delivery metrics, and structured logging. Trigger with phrases like "shopify monitoring", "shopify metrics", "shopify observability", "monitor shopify API", "shopify alerts", "shopify dashboard".
salesforce-observability
Set up observability for Salesforce integrations with API limit monitoring, error tracking, and alerting. Use when implementing monitoring for Salesforce operations, tracking API consumption, or configuring alerting for Salesforce integration health. Trigger with phrases like "salesforce monitoring", "salesforce metrics", "salesforce observability", "monitor salesforce", "salesforce alerts", "salesforce API usage dashboard".
retellai-observability
Retell AI observability — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony. Trigger with phrases like "retell observability", "retellai-observability", "voice agent".
replit-observability
Monitor Replit deployments with health checks, uptime tracking, resource usage, and alerting. Use when setting up monitoring for Replit apps, building health dashboards, or configuring alerting for deployment health and performance. Trigger with phrases like "replit monitoring", "replit metrics", "replit observability", "monitor replit", "replit alerts", "replit uptime".