CtrlK
BlogDocsLog inGet started
Tessl Logo

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

Quality

92%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

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 strong, well-structured skill that provides highly actionable debugging workflows for Flux CD clusters. The five workflows cover the major resource types with clear step-by-step sequences, appropriate cross-references, and good edge case handling. Minor improvements could be made in conciseness by reducing repetition across workflows and potentially offloading the CRD table to a reference file.

DimensionReasoningScore

Conciseness

The skill is generally well-structured and avoids explaining basic Kubernetes or Flux concepts, but there is some repetition across workflows (e.g., step 1 of every workflow calls get_flux_instance with similar phrasing). The CRD reference table is useful but lengthy; it could be offloaded to a reference file. Some edge cases describe things Claude could infer (e.g., what suspended resources mean).

2 / 3

Actionability

The skill provides highly specific, concrete guidance: exact MCP tool names to call, exact fields to inspect (chartRef, sourceRef, valuesFrom, substituteFrom), specific analysis steps, and a clear report format. While there are no bash commands or code blocks, this is an instruction-only skill where the actions are MCP tool calls, and each step is unambiguous and directly executable.

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 Ready: True, check controller status before proceeding, wait for progressing resources). Cross-references between workflows (e.g., Workflow 4 step 6 references Workflows 2 and 3) create appropriate feedback loops. The edge cases section handles error recovery scenarios well.

3 / 3

Progressive Disclosure

The skill provides a clear overview with well-signaled references to deeper content: references/flux-crds.md for detailed CRD descriptions, references/troubleshooting.md for failure patterns, and assets/schemas/ for OpenAPI schemas. Each reference includes guidance on when to load it. The CRD reference table serves as a quick-lookup index. Navigation is one level deep and clearly signaled.

3 / 3

Total

11

/

12

Passed

Description

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 set of natural trigger terms, explicitly answers both what and when, and carves out a clear niche that distinguishes it from related skills. The explicit scoping to live clusters (not local repo files) is a particularly strong differentiator.

DimensionReasoningScore

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 via Flux MCP server, not local repo files.

3 / 3

Completeness

Clearly answers both 'what' (debug/troubleshoot Flux CD on live clusters — inspects status, reads logs, traces dependencies, health checks) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios like failing resources, reconciliation errors, and controller issues.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'Flux CD', 'Kubernetes clusters', 'reconciliation errors', 'controller issues', 'artifact pull failures', 'not-ready Flux resources', 'stuck', 'failing', 'Flux Operator troubleshooting'. These closely match how users describe Flux problems.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — explicitly scoped to Flux CD on live Kubernetes clusters via the Flux MCP server, and explicitly excludes local repo files. The combination of Flux-specific terminology and live cluster context makes it very unlikely to conflict with general Kubernetes, GitOps, or file-based skills.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
fluxcd/agent-skills
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.