CtrlK
BlogDocsLog inGet started
Tessl Logo

kubernetes-deployment

Kubernetes deployment workflow for container orchestration, Helm charts, service mesh, and production-ready K8s configurations.

38

Quality

36%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/kubernetes-deployment/SKILL.md

The canonical home for this skill is kubernetes-deployment in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

21%Scale 1-5

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

This skill is essentially a table of contents or orchestration outline that delegates all actual work to external skills without providing any concrete, executable guidance itself. It contains no code examples, no YAML manifests, no specific commands, and no validation steps — just vague action lists repeated across 7 identically-structured phases. The content fails to teach Claude anything it doesn't already know about Kubernetes deployment workflows.

Suggestions

Add concrete, executable examples for at least the core phases — e.g., a sample Deployment YAML, a Helm chart skeleton, kubectl commands for verification, and a basic NetworkPolicy manifest.

Replace vague action items like 'Create Deployment' and 'Configure RBAC' with specific commands and configurations (e.g., `kubectl apply -f deployment.yaml`, `helm install --dry-run`).

Add explicit validation checkpoints between phases with concrete verification commands (e.g., `kubectl get pods -w`, `helm lint ./chart`, `kubectl auth can-i --list`) and error recovery guidance.

Either provide the referenced external skill files in the bundle or inline the essential guidance — currently the skill delegates everything to nonexistent skills, leaving Claude with no actionable content.

DimensionReasoningScore

Conciseness

The skill is heavily padded with repetitive structure across 7 phases, each following the same template of 'Skills to Invoke / Actions / Copy-Paste Prompts' without adding substantive content. The numbered action lists are vague bullet points that don't convey information Claude doesn't already know (e.g., 'Create Dockerfile', 'Build container image'). The 'When to Use This Workflow' section restates the overview.

2 / 5

Actionability

There is no executable code, no concrete commands, no YAML examples, no specific configurations — nothing Claude could actually execute. Every 'action' is a vague directive like 'Create Deployment' or 'Configure RBAC', and the 'Copy-Paste Prompts' just say 'Use @skill-name to do X' which delegates all actual work to unspecified external skills without providing any real guidance.

1 / 5

Workflow Clarity

While there is a rough 7-phase sequence, the steps within each phase are superficial lists with no specifics. There are no validation checkpoints between phases, no feedback loops, and no error recovery guidance. The 'Quality Gates' checklist at the end is a set of vague checkboxes with no criteria for what 'working' or 'valid' means. For a workflow involving destructive/batch deployment operations, the lack of validation caps this at 3, but the overall vagueness brings it to 2.

2 / 5

Progressive Disclosure

The skill references many external skills and workflow bundles, suggesting a multi-file structure, but none of these referenced files exist in the bundle. The structure within the file is organized with clear sections and phases, but the content that should be in the main file (actual instructions, examples) is absent, and the references point to skills that may or may not exist.

3 / 5

Total

8

/

20

Passed

Description

52%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.

The description identifies the Kubernetes domain and includes several relevant technical terms that serve as decent trigger keywords. However, it lacks concrete action verbs describing what the skill does and entirely omits a 'Use when...' clause, making it unclear when Claude should select this skill over others. It reads more like a topic tag list than a functional skill description.

Suggestions

Add a 'Use when...' clause with explicit trigger phrases, e.g., 'Use when the user asks about deploying to Kubernetes, writing Helm charts, configuring services, or setting up K8s clusters.'

Replace the topic-listing style with concrete action verbs, e.g., 'Generates Kubernetes manifests, creates Helm charts, configures service mesh routing, and sets up production-ready deployment pipelines.'

Include additional natural trigger terms and synonyms like 'kubectl', 'pods', 'namespaces', 'YAML manifests', 'cluster', and 'ingress' to improve discoverability.

DimensionReasoningScore

Specificity

Names the domain (Kubernetes) and lists several related concepts (Helm charts, service mesh, production-ready configurations), but these are more like topic areas than concrete actions. No specific verbs describe what the skill actually does (e.g., 'generates manifests', 'configures ingress', 'sets up rolling deployments').

3 / 5

Completeness

Provides a partial 'what' (deployment workflow, Helm charts, service mesh, configurations) but has no explicit 'when' clause. The absence of a 'Use when...' clause caps this at 3 per the rubric, and the 'what' is more of a topic list than a clear explanation, bringing it to 2.

2 / 5

Trigger Term Quality

Includes good natural keywords like 'Kubernetes', 'K8s', 'Helm charts', 'service mesh', 'container orchestration', and 'deployment'. Missing some common variations like 'kubectl', 'pods', 'namespaces', 'YAML manifests', '.yaml', or 'cluster'.

4 / 5

Distinctiveness Conflict Risk

Kubernetes/K8s is a fairly distinct domain, and the mention of Helm charts and service mesh narrows the scope further. Minor overlap risk with general Docker/container skills or generic DevOps/infrastructure skills, but mostly distinguishable.

4 / 5

Total

13

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.