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 hits all the marks. It provides specific concrete actions, includes a comprehensive 'Use when...' clause with natural trigger terms, clearly scopes itself to live Kubernetes clusters (excluding local files), and occupies a distinct niche that minimizes conflict risk with other 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, inspect status, read logs, trace dependencies, health checks) and 'when' (explicit 'Use when...' clause listing specific trigger scenarios like failing resources, reconciliation errors, controller issues). | 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', 'Flux CD', 'Kubernetes clusters'. These are terms a user experiencing Flux issues would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Flux CD on live Kubernetes clusters via Flux MCP server) and explicitly excludes local repo files. The combination of Flux CD, live cluster, and MCP server makes it very unlikely to conflict with other 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, actionable workflows for troubleshooting Flux CD on live clusters. The five debugging workflows are clearly sequenced with appropriate validation steps and cross-references. Minor verbosity in edge cases and general rules sections could be tightened, and the large CRD reference table could potentially be offloaded to a reference file to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and domain-specific, but some sections are slightly verbose — e.g., the General Rules section explains things like 'Secrets return empty values' and the edge cases section includes guidance Claude could infer (like 'don't flag suspended resources as errors'). The CRD reference table is valuable but lengthy; it could be offloaded to a reference file. | 2 / 3 |
Actionability | The skill provides highly concrete, step-by-step guidance with specific MCP tool calls (get_flux_instance, get_kubernetes_resources, get_kubernetes_logs), 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 immediately usable. | 3 / 3 |
Workflow Clarity | Five distinct workflows are clearly sequenced with numbered steps, each building logically from resource inspection to dependency tracing to root cause analysis. Validation checkpoints are present (e.g., verify FluxInstance Ready: True, check controller status before proceeding, verify dependencies are Ready). Cross-references between workflows (e.g., Workflow 4 step 6 references Workflows 2 and 3) provide clear feedback loops. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references: OpenAPI schemas in assets/schemas/, detailed CRD descriptions in references/flux-crds.md, and troubleshooting patterns in references/troubleshooting.md. The Loading References section explicitly tells Claude when to consult each file. | 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.
4ba2c61
Table of Contents
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.