running-stabilization-loop

Use after major refactors or risky infrastructure changes to run iterative stabilization loops in kube-test: clean state, run the v3 matrix (k3s/rke2, autoscaler, leapmicro/microos, multi-arch), proactively debug failures over SSH/journalctl, apply fixes, retest until green, then validate upgrade paths from the latest tag to the current release-candidate branch.

Quality

88%

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

85%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-sequenced runbook with strong validation and feedback loops for a destructive/batch workflow. Its main weakness is progressive disclosure: a large monolithic file with no references, where the buddy prompt and failure catalog could live in separate files.

Suggestions

Move the Buddy Prompt Template into references/buddy-prompt.md and link to it, reducing duplication with the step sections and shrinking the inline body.

Extract the 'Known high-frequency failures to check first' catalog into references/known-failures.md, keeping only a one-line pointer plus the most common case inline.

Factor the repeated terraform/tofu validation gate block (Steps 1 and 6) into a single referenced snippet or a scripts/validate-gates.sh to remove the verbatim duplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, executable commands with little explanation of concepts Claude already knows, but the Buddy Prompt Template restates the step goals and the terraform/tofu gate block is repeated verbatim in Steps 1 and 6, which could be factored out.	4 / 5
Actionability	Fully executable copy-paste bash with concrete paths, named scenarios, specific journalctl/systemctl checks, and clearly marked placeholders like <node-ip> and <failed-scenarios>; covers the common matrix and debug cases.	5 / 5
Workflow Clarity	A 9-step sequence with a dot-graph, explicit validation checkpoints (terraform/tofu validate, full regression rerun, upgrade-path tests), feedback loops (fix -> targeted rerun -> full rerun), an Invariants checklist, and dry-run inspection guidance before the destructive force cleanup.	5 / 5
Progressive Disclosure	There are no bundle files and the ~390-line SKILL.md is monolithic; the Buddy Prompt Template and the known high-frequency failure catalog are inlined rather than split into referenced files, so structure exists but content that should be separate remains inline.	3 / 5
	Total	17 / 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, concrete description that clearly states both capabilities and trigger conditions for a narrowly scoped stabilization-loop skill. Trigger synonym coverage is the only soft spot, keeping trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "clean state, run the v3 matrix (k3s/rke2, autoscaler, leapmicro/microos, multi-arch)", "proactively debug failures over SSH/journalctl", "apply fixes, retest until green", "validate upgrade paths from the latest tag to the current release-candidate branch" — giving comprehensive coverage rather than just 1-2 actions.	5 / 5
Completeness	Explicitly answers both what ("run iterative stabilization loops in kube-test" with enumerated sub-actions) and when ("Use after major refactors or risky infrastructure changes"), with concrete trigger phrasing rather than weak implication.	5 / 5
Trigger Term Quality	"Use after major refactors or risky infrastructure changes" are natural phrases a user would say, but the trigger vocabulary is narrow with few synonyms or common variations beyond those two phrases.	4 / 5
Distinctiveness Conflict Risk	The kube-test / v3-matrix / kube-hetzner / k3s-rke2 niche is highly specific with distinct triggers, making overlap with unrelated skills minimal.	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: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/running-stabilization-loop/SKILL.md
Commit: bb1622c

Reviewed: 1 day 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.