CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

operator-audit

Run the full Kubernetes Operator audit (CRD + reconcile + capability) on the current repo

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable skill body: an executable implementation with concrete paths and fallbacks, clear sequencing, and disciplined section organization. The only notable weaknesses are the opaque skill-path variable and failure swallowing that weakens the validation feedback loop.

Suggestions

Explain or dynamically resolve the SKILL variable (e.g., relative to the skill's install directory) so the commands are runnable without knowing where the kubernetes-operator skill lives.

Replace bare "|| true" with guidance to report script failures in the report (e.g., emit a FAIL section) so validation gaps surface instead of being silently dropped.

DimensionReasoningScore

Conciseness

The body is lean and every section earns its place — a numbered overview, usage invocations, an executable script, output spec, and pre/post-conditions — with no explanation of concepts Claude already knows, matching the lean/efficient anchor exactly.

5 / 5

Actionability

The Implementation block is concrete, runnable bash with flags, an env-var default, and a fallback for the internal/controller layout; the unexplained SKILL=engineering/kubernetes-operator/... path assumption is a minor gap that keeps it below fully copy-paste ready.

4 / 5

Workflow Clarity

The four numbered steps map one-to-one onto executable commands with defined exit-code post-conditions, and the audit scripts themselves act as validators; however, "|| true" silently swallows failures of the first two scripts with no recovery guidance, a minor validation gap versus the explicit feedback-loop anchor.

4 / 5

Progressive Disclosure

This is a short single-purpose skill with no bundle files and nothing that belongs in a separate file; its well-organized sections (Usage, Implementation, Output, Pre-conditions, Post-conditions) satisfy the simple-skill exception for full marks.

5 / 5

Total

18

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive, appropriately concise description that clearly conveys what the skill does, but it lacks any "when to use" trigger guidance, which caps its completeness and leaves trigger-term coverage good rather than comprehensive.

Suggestions

Append a trigger clause such as "Use when the user asks to audit, review, or score a Kubernetes operator, its CRDs, or its reconcile loops" to fix the completeness gap.

Add one or two natural synonyms (e.g., "custom resources", "controller") to broaden trigger-term coverage without padding the description.

DimensionReasoningScore

Specificity

"Run the full Kubernetes Operator audit (CRD + reconcile + capability)" names the domain and enumerates three concrete audit areas, matching the several-specific-actions anchor; it falls short of 5 because coverage is compressed into a parenthetical and the actual actions (validate, lint, score) are not individually named.

4 / 5

Completeness

The description clearly answers "what" (run the CRD + reconcile + capability audit) but has no "Use when..." clause; "on the current repo" only weakly implies timing, and the guidelines cap completeness at 3 without explicit trigger guidance.

3 / 5

Trigger Term Quality

"Kubernetes Operator", "audit", "CRD", "reconcile", and "capability" are natural terms users of this domain would say, giving good keyword coverage; a few common variations such as "controller", "custom resource", or "OperatorHub" are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (operator auditing via CRD, reconcile, and capability checks) with distinct domain triggers, making accidental activation of unrelated skills minimal.

5 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alirezarezvani/claude-skills

Path

.gemini/skills/operator-audit/SKILL.md

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.