multi-branch-cluster-setup

Set up N isolated minikube clusters, one per Git worktree, for parallel Ark branch development. Use when the user wants to run multiple branches simultaneously, set up isolated Kubernetes environments per branch, create git worktrees with dedicated clusters, or configure devspace contexts for multi-branch development.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%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 highly actionable, well-structured skill body that delegates implementation to bundled scripts and includes solid troubleshooting. The main weakness is a destructive batch operation (deleting all minikube profiles) lacking a validation/confirmation checkpoint.

Suggestions

Add an explicit validation/confirmation step before Step 3 destroys all existing minikube profiles — e.g., prompt the user or list affected profiles first and require confirmation, since this is a destructive batch operation that currently caps workflow_clarity at 3.

Consider moving the large manual helm deploy block in Step 4 into a referenced script or reference file so the SKILL.md body stays a lean overview.

Tighten the branch-count explanation ('2 branches = 2 clusters, 4 branches = 4 clusters, etc.') since the table and port formula already convey this.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence with dense, task-relevant commands; minor verbosity in spots like '2 branches = 2 clusters, 4 branches = 4 clusters, etc.' that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready bash/helm/devspace commands throughout, with specific examples covering deployment, image transfer, port forwarding, and manual fallbacks for the common failure cases.	5 / 5
Workflow Clarity	Steps 1–6 are clearly sequenced with some verification commands, but the workflow is capped at 3 because Step 3's setup script destructively 'Deletes all existing minikube profiles' as a batch operation with no validation or confirmation checkpoint.	3 / 5
Progressive Disclosure	Implementation is appropriately delegated to four real, one-level-deep scripts (setup-clusters.sh, transfer-images.sh, deploy-helm.sh, port-forward.sh) with clear full-path references and well-organized sections; some inline bulk in the manual helm block keeps it from a 5.	4 / 5
	Total	16 / 20 Passed

Description

92%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, niche-specific description that clearly states what the skill does and when to invoke it, using concrete actions and natural trigger terms. Minor synonym coverage is the only gap.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Set up N isolated minikube clusters, one per Git worktree', 'create git worktrees with dedicated clusters', 'configure devspace contexts' — with comprehensive coverage of the skill's domain.	5 / 5
Completeness	Explicitly answers both 'what' (set up N isolated minikube clusters, one per Git worktree, for parallel Ark branch development) and 'when' (Use when the user wants to run multiple branches simultaneously...) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage — 'run multiple branches simultaneously', 'isolated Kubernetes environments per branch', 'git worktrees', 'multi-branch development' — terms a user would actually say, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (per-branch minikube clusters for Ark development) with distinct, specific triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: mckinsey/agents-at-scale-ark
Path: .claude/skills/multi-branch-cluster-setup/SKILL.md
Commit: b018d5b

Reviewed: 12 hours ago

Table of Contents

Discovery Implementation Validation

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.