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.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 troubleshooting on live clusters), lists concrete actions, provides explicit trigger guidance via a 'Use when...' clause with natural user terms, and distinguishes itself from related skills by specifying the mechanism (Flux MCP server) and excluding local repo files. It follows all best practices and uses proper third-person voice throughout.
| 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 mechanism ('via the Flux MCP server') and scope ('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: 'Flux CD', 'Kubernetes clusters', 'failing', 'stuck', 'not-ready', 'reconciliation errors', 'controller issues', 'artifact pull failures', 'Flux Operator troubleshooting'. These are exactly the terms a user experiencing Flux issues would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — narrowly scoped to Flux CD on live Kubernetes clusters via a specific MCP server, and explicitly excludes local repo files. Very unlikely to conflict with general Kubernetes skills, GitOps skills, or local file editing 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 skill that provides comprehensive debugging workflows for Flux CD on Kubernetes clusters. The workflows are concrete and actionable with specific tool calls, clear sequencing, and good edge case handling. The only minor weakness is some verbosity that could be trimmed — the introductory paragraph and some workflow preambles restate information that could be implied.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is generally efficient and domain-specific, but some sections are slightly verbose — e.g., the introductory paragraph restating what the skill does, and some workflow steps that could be more terse. The CRD reference table is valuable but lengthy; it could be offloaded to a reference file. Overall mostly efficient with room to tighten. | 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.), exact field names to inspect (chartRef, sourceRef, valuesFrom, substituteFrom), 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), and feedback loops (e.g., if resources are failing, follow sub-workflows). The edge cases section handles error recovery scenarios. The instruction to adapt depth based on user request is a smart meta-workflow. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections, then points to one-level-deep references (references/flux-crds.md, references/troubleshooting.md, assets/schemas/) with explicit guidance on when to load them. The CRD table serves as a quick-reference inline while deeper details are properly externalized. | 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
a8f177b
- 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.