Agent skill · data analytics · jeremylongshore
coreweave-gpu-cost-leak-hunter
Hunt down CoreWeave GPU cost leaks — idle reserved capacity, wrong-GPU-type right-sizing waste, allocated-but-idle instances, and on-demand spend that should be committed — then produce a CFO-grokkable, dollar-ranked FinOps report. CoreWeave ships no cost dashboard and no billing API, so the spend view is built from PromQL against its managed Grafana. Use when a user asks why their CoreWeave GPU bill is high, wants to find wasted GPU spend or idle reservations, or needs a GPU FinOps cost report. Trigger with "coreweave cost", "why is my coreweave bill", "wasted GPU spend", "idle reserved capacity", "GPU cost leak".
Why this skill is useful
Adds a complete executable pipeline for auditing GPU costs on CoreWeave, including PromQL queries and a ranking script that the AI cannot generate from existing knowledge.
What it needs
Requires jq, python3 installed locally. Requires coreweave account access. About 8k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
CoreWeave GPU Cost Leak Hunter Community-contributed. Not affiliated with, endorsed by, or sponsored by CoreWeave, Inc. CoreWeave is a registered trademark of CoreWeave, Inc. Audits a CoreWeave GPU cluster for real-dollar cost leaks — idle reserved capacity, GPUs on the wrong SKU, allocated-but-idle instances, and steady on-demand spend that should be committed — then emits a CFO-grokkable, dollar-ranked FinOps report. Overview CoreWeave ships no cost dashboard and no billing API ([usage-monitoring docs][um]). There is also no single "dollars" metric — spend is reconstructed by querying usage from CoreWeave's managed Grafana in PromQL and multiplying each resource's usage by its rate-card price. This skill does exactly that, then ranks the leaks by monthly dollar impact. The math is deterministic: PromQL returns usage counts, and the bundled scripts/rank-and-report.py does every multiplication, sum, and ranking — the agent never eyeballs a number. Two of the four categories are billed waste (Confirmed); the other two are a right-sizing model (Estimated) and a commitment decision (At-risk), labeled so a CFO never reads a modeled number as recoverable cash. Deep domain knowledge lives in references/, loaded only when a leak needs it. Prerequisites CoreWeave managed Grafana access — the Prometheus data source is reachable only to a member of the admin, metrics, or write group in the CoreWeave Cloud Console ([usage-monitoring docs][um]). This is the hard dependency; Step 1 probes it and fails fast if the group is missing. A Prometheus/Grafana query endpoint in $CWPROMURL (the Grafana data-source proxy, e.g. https://grafana.ORG.coreweave.com/api/datasources/proxy/uid/UID) and a bearer token in $CWTOKEN for curl. kubeconfig for the cluster (CoreWeave-issued) so kubectl get can corroborate live GPU allocation and node labels. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/coreweave-gpu-cost-leak-hunter--6b7fb8