upgrade-cluster

Use when upgrading or hardening an existing kube-hetzner cluster, including module version bumps, provider lockfile refreshes, k3s/RKE2 channel/version upgrades, immutable node replacement, system-upgrade-controller changes, or live cluster rollout validation

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a tightly structured, highly actionable runbook with explicit validation checkpoints and stop conditions appropriate to a destructive live-cluster operation, and it uses progressive disclosure well via a real one-level-deep reference. Its only weakness is mild verbosity and a couple of referenced scripts that are not present in the bundle.

Suggestions

Trim explanatory rationale and move the long inline existing-node interface-rename procedure into a reference file to lift conciseness toward the lean score-3 anchor.

Either add the referenced 'scripts/destroy.sh' and 'scripts/cleanup.sh' to the bundle or replace those references with inline minimal commands so no referenced path is missing.

Consider moving the SELinux and capacity/plan-shape sub-sections into the immutable-node-replacement reference to keep the SKILL.md body as a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~370-line body largely assumes Claude's competence (no explanations of Kubernetes/Terraform/etcd) and keeps sections lean, but some explanatory rationale and a long inline interface-rename procedure could be tightened or moved to the reference, so it sits at the 'mostly efficient but could be tightened' score-2 anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Copy-paste-ready commands with real flags appear throughout — 'terraform init -upgrade -input=false', 'terraform plan -input=false -parallelism=1 -out=module-upgrade.tfplan', a real jq pipeline over 'terraform show -json', and 'ssh root@<node-ip> "... /etc/cloud/rename_interface.sh; ..."' — matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	A clear phased sequence (Preflight, Module Convergence, Runtime Upgrade, Immutable Replacement, Health Checks, Firewall Closure, Final Report) with explicit validation checkpoints and stop conditions — 'Any output is a stop condition. Root-cause it before apply.', detailed-exitcode re-plans, and 'require the normal proof again' after repair — exceeds the score-3 anchor for a risky operation.	3 / 3
Progressive Disclosure	The body is an overview that correctly offloads the bulk of Phase 3 to a one-level-deep, clearly-signaled and verified-present 'references/immutable-node-replacement.md', matching the clear-overview-with-well-signaled-one-level-deep-references score-3 anchor; minor gap: 'scripts/destroy.sh' and 'scripts/cleanup.sh' are referenced but no scripts/ bundle exists.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is concise, action-specific, and leads with an explicit 'Use when' trigger that tightly scopes the skill to kube-hetzner cluster upgrades and hardening. It answers both what and when with concrete, distinctive terms and no vague filler.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'module version bumps', 'provider lockfile refreshes', 'k3s/RKE2 channel/version upgrades', 'immutable node replacement', 'system-upgrade-controller changes', 'live cluster rollout validation' — matching the score-3 anchor of multiple specific concrete actions rather than the partial score-2 anchor.	3 / 3
Completeness	Opens with an explicit 'Use when' trigger and an 'including ...' enumeration that concretely answers what the skill does, satisfying both what and when with explicit triggers as required for score 3.	3 / 3
Trigger Term Quality	Natural operator phrasing ('upgrading or hardening an existing kube-hetzner cluster', 'module version bumps', 'k3s/RKE2 channel/version upgrades') plus the distinctive 'kube-hetzner' project name give good coverage of terms an operator would actually say, beyond the score-2 'missing common variations' anchor.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and named (upgrading/hardening a specific kube-hetzner cluster) with module/provider/k3s/RKE2-specific triggers unlikely to fire for unrelated skills, matching the clear-niche score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/upgrade-cluster/SKILL.md
Commit: a8b696d

Reviewed: 11 days 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.