CtrlK
BlogDocsLog inGet started
Tessl Logo

ark-setup-cluster

Set up and install the Ark platform in a Kubernetes cluster. Supports default mode (existing cluster) and isolated e2e testing mode (dedicated Kind cluster). Use when the user wants to install, deploy, test, or configure Ark.

68

Quality

83%

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

82%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 well-structured, highly actionable install runbook with concrete commands, a critical pre-check for destructive cluster operations, and clear verification. Conciseness and the verify-step feedback loop have minor room to improve.

Suggestions

Trim or remove the 'When to use this skill' section, which duplicates the frontmatter description.

Replace the prose verify instruction ('Wait until all pods show Running and Ready') with an executable wait command such as `kubectl wait --for=condition=Ready pods --all -n default --timeout=5m`.

Add an explicit retry/feedback loop in Step 4 (on failure, jump to Troubleshooting) to mirror the validate->fix->retry pattern used in Step 0.

DimensionReasoningScore

Conciseness

Mostly lean and command-driven with no over-explanation of concepts Claude knows, though the 'When to use this skill' section partly restates the frontmatter description and could be trimmed.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands throughout (kind create cluster, npm install/build, node ... install --yes --wait-for-ready 5m, helm install) with appropriately parameterized placeholders for variable values.

5 / 5

Workflow Clarity

Clear numbered sequence (Step 0 check -> Step 5 cleanup) with a critical pre-check and a verify step ('Wait until all pods show Running and Ready'), plus a troubleshooting feedback section; the verify step lacks a concrete wait/retry command, leaving a minor gap.

4 / 5

Progressive Disclosure

Well-organized into clear sections (Prerequisites, Steps 0-5, Troubleshooting, Important) with no nested references; all content is appropriately self-contained since no external detail files are needed, though it exceeds the under-50-line simple-skill carve-out.

4 / 5

Total

17

/

20

Passed

Description

83%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 strong, third-person description that clearly states what the skill does and when to use it with concrete trigger terms. Minor gains possible by adding more granular action specifics and synonyms.

DimensionReasoningScore

Specificity

Names the domain (Ark platform, Kubernetes cluster, Kind) and several concrete actions ('Set up and install', 'install, deploy, test, or configure') plus two distinct modes, but the action verbs are somewhat generic rather than granular.

4 / 5

Completeness

Explicitly answers both 'what' ('Set up and install the Ark platform in a Kubernetes cluster... Supports default mode... and isolated e2e testing mode') and 'when' ('Use when the user wants to install, deploy, test, or configure Ark') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user-facing phrases like 'install, deploy, test, or configure Ark' are present and would be said verbatim, though a few common synonyms/variants are missing.

4 / 5

Distinctiveness Conflict Risk

The 'Ark platform' / Kind-specific framing carves a clear niche with low conflict risk, though generic verbs like 'deploy'/'configure' leave minor overlap with adjacent deployment skills.

4 / 5

Total

17

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
mckinsey/agents-at-scale-ark
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.