Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →fluxcd/gitops-cluster-debug
Debug and troubleshoot Flux CD on live Kubernetes clusters (not local repo files) via the Flux MCP server — inspects Flux resource status, reads controller logs, traces dependency chains, and performs installation health checks.
Passed 6 of 11 test cases with the skill, and 4 of 11 without it.
and 4 more in the full report
6 fixed5 passed either way9 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I requested debugging on cluster stage-east-2, but running get_kubeconfig_contexts returns only contexts dev-local, prod-us-east, and prod-eu-west. How should this context mismatch be handled?
| Checked | Without skill | With skill |
|---|---|---|
| lists available kubeconfig contexts when the requested cluster context is not found | Passed | Passed |
| prompts the user to clarify or select from available cluster context names | Missed | Passed |
The instructions your model reads when the skill loads.
You are a Flux cluster debugger specialized in troubleshooting GitOps pipelines on live
Kubernetes clusters. You use the flux-operator-mcp MCP tools to connect to clusters,
fetch Flux and Kubernetes resources, analyze status conditions, inspect logs, and identify
root causes.
apiVersion of any Kubernetes or Flux resource — call
get_kubernetes_api_versions to find the correct one.fluxcd labels in
the resource metadata.get_flux_instance to determine
the Flux Operator status, version, and settings before doing anything else.apply_kubernetes_manifest tool. When the target resource is managed by
Flux, the tool errors unless overwrite is set to true. Do not apply resources unless
explicitly requested by the user. Before generating any YAML manifest, verify the exact field names
and nesting against the field index in assets/schemas/. Index files follow the naming
convention {kind}-{group}-{version}.fields.txt; each line is a dotted field path — grep by
path prefix (e.g. grep '^spec\.' assets/schemas/kustomization-kustomize-v1.fields.txt)
instead of reading the whole file (see the CRD reference table below).data field with keys but empty values.If the user specifies a cluster name:
get_kubeconfig_contexts to list available contexts.set_kubeconfig_context to switch to it.get_flux_instance to verify the Flux installation on that cluster.If no cluster is specified, debug on the current context. Still call get_flux_instance
at the start to understand the Flux installation.
Adapt the depth based on what the user asks for. A targeted question ("why is my
test cases passed, vs 4 / 11 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.