CtrlK
BlogDocsLog inGet started
Tessl Logo

kubernetes-architect

Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Masters EKS/AKS/GKE, service mesh (Istio/Linkerd), progressive delivery, multi-tenancy, and platform engineering. Handles security, observability, cost optimization, and developer experience. Use PROACTIVELY for K8s architecture, GitOps implementation, or cloud-native platform design.

52

Quality

59%

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 ./skills/kubernetes-architect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

31%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.

The body reads as a persona-and-capability catalog rather than actionable architecture guidance: it enumerates technology landscapes Claude already knows and duplicates workflow steps, with no external references and abstract instructions. It is well-sectioned but padded and lacks executable specifics.

Suggestions

Move the 'Capabilities' technology catalog and 'Knowledge Base' into a reference file (e.g. references/capabilities.md) and keep SKILL.md as a concise overview with clearly signaled links.

Replace abstract Instructions ('Define cluster topology', 'Choose GitOps tooling') with concrete, executable artifacts — starter manifests, Helm/Kustomize commands, or decision templates.

Trim 'Behavioral Traits' and merge the redundant 'Response Approach' into 'Instructions', adding explicit validate-in-staging → rollback checkpoints to the workflow.

DimensionReasoningScore

Conciseness

The ~158-line body is noticeably verbose: the 'Capabilities' section is a giant catalog of CNCF tools, and 'Behavioral Traits' and 'Knowledge Base' restate concepts Claude already knows, with 'Response Approach' largely duplicating 'Instructions'.

2 / 5

Actionability

Guidance is high-level and abstract ('Gather workload requirements', 'Define cluster topology', 'Choose GitOps tooling') with no concrete commands, templates, manifests, or executable specifics — only minimal concrete guidance beyond prompting-style example interactions.

2 / 5

Workflow Clarity

A sequenced process exists ('Instructions' has 4 ordered steps and 'Response Approach' has 9), and the Safety section adds staging/rollback guidance, but validation checkpoints are implicit rather than explicit feedback loops.

3 / 5

Progressive Disclosure

No bundle files or external references exist; the large 'Capabilities' catalog and 'Knowledge Base' that clearly belong in separate reference files are inlined into a single monolithic document despite decent section headers.

2 / 5

Total

9

/

20

Passed

Description

87%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 well-constructed description that answers both 'what' and 'when' explicitly with strong, niche-specific trigger terms in third-person voice. The main weakness is verb-genericity — capabilities are named as domains rather than discrete concrete actions.

DimensionReasoningScore

Specificity

The description lists several concrete capability areas ('advanced GitOps workflows (ArgoCD/Flux)', 'service mesh (Istio/Linkerd)', 'progressive delivery, multi-tenancy'), but the verbs ('specializing in', 'Masters', 'Handles') are generic and applied to domain nouns rather than naming discrete actions like 'extract', 'fill', 'merge'.

4 / 5

Completeness

It explicitly states both what ('Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows...') and when ('Use PROACTIVELY for K8s architecture, GitOps implementation, or cloud-native platform design'), matching the anchor for clear what-and-when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural-term coverage with synonyms ('Kubernetes'/'K8s') and provider/tool names ('EKS/AKS/GKE', 'ArgoCD/Flux', 'Istio/Linkerd'), but a few common user phrases ('cluster', 'deploy', 'kubectl') are absent.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Kubernetes platform architecture / GitOps) with distinct, specific triggers that are unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
rmyndharis/antigravity-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.