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. Use when users report failing, stuck, or not-ready Flux resources on a cluster, reconciliation errors, controller issues, artifact pull failures, or need live cluster Flux Operator troubleshooting.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its scope (Flux CD on live clusters, not local files), lists specific concrete actions, and provides comprehensive trigger terms in an explicit 'Use when...' clause. The description is well-structured, uses third person voice throughout, and is distinctive enough to avoid conflicts with related Kubernetes or GitOps skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'inspects Flux resource status', 'reads controller logs', 'traces dependency chains', 'performs installation health checks'. Also specifies the scope clearly (live Kubernetes clusters, not local repo files). | 3 / 3 |
Completeness | Clearly answers both 'what' (debug/troubleshoot Flux CD via MCP server with specific actions listed) and 'when' (explicit 'Use when...' clause covering failing resources, reconciliation errors, controller issues, artifact pull failures, and live cluster troubleshooting). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'failing', 'stuck', 'not-ready Flux resources', 'reconciliation errors', 'controller issues', 'artifact pull failures', 'Flux Operator troubleshooting', 'Kubernetes clusters', 'Flux CD'. These are terms a user experiencing Flux issues would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — narrowly scoped to Flux CD on live Kubernetes clusters via the Flux MCP server, explicitly excluding local repo files. The combination of Flux CD, live cluster, and MCP server creates a very clear niche unlikely to conflict with general Kubernetes or GitOps skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, well-structured debugging skill that provides concrete, tool-specific workflows for troubleshooting Flux CD on live clusters. Its greatest strengths are the clear multi-step workflows with explicit tool calls and decision points, the comprehensive CRD reference table, and the well-organized progressive disclosure to reference files. Minor verbosity in edge cases and general rules prevents a perfect conciseness score, but overall the content is highly actionable and well-organized.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and domain-specific, but some sections are slightly verbose — e.g., the General Rules preamble and the Edge Cases section include guidance Claude could infer (like 'don't flag suspended resources as errors unless the user expects it to be active'). The CRD reference table is valuable but lengthy; it could be offloaded to a reference file. | 2 / 3 |
Actionability | Every workflow provides concrete, step-by-step instructions with specific MCP tool calls (get_flux_instance, get_kubernetes_resources, get_kubernetes_logs, etc.), specific fields to inspect (chartRef, sourceRef, valuesFrom, matchLabels), and clear decision points. The CRD reference table with exact apiVersions and schema file paths is highly actionable. | 3 / 3 |
Workflow Clarity | Five distinct workflows are clearly sequenced with numbered steps, explicit validation checkpoints (e.g., verify Ready: True, check controller status before proceeding), conditional branching (e.g., 'if managed resources are failing, analyze their logs'), and cross-references between workflows (e.g., Workflow 4 references Workflows 2 and 3). The report format provides a structured output template. Edge cases cover error recovery scenarios. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references: detailed CRD field descriptions in references/flux-crds.md, troubleshooting patterns in references/troubleshooting.md, and OpenAPI schemas in assets/schemas/. The Loading References section clearly signals when to consult each file. The main body stays at the right level of detail for an overview. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- fluxcd/agent-skills
- Commit
fec8a8f
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.