debug-node

Use when a Hetzner node is unreachable, SSH fails, cloud-init seems broken, or provisioning hangs. Boots into rescue mode via hcloud CLI to inspect filesystem, logs, SSH keys, sshd config, and cloud-init state without needing SSH access to the node itself.

Quality

96%

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

92%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.

A highly actionable, well-sequenced debugging playbook with executable commands, validation checkpoints, and a strong diagnostic checklist. Its main weakness is progressive disclosure: it is monolithic and cites external files that are not actually bundled.

Suggestions

Create the referenced `docs/selinux.md`, `scripts/destroy.sh`, and `scripts/cleanup.sh` as real bundle files (or remove the references) so navigation targets resolve.

Move the SELinux workflow detail (Step 5h plus the surrounding policy guidance) into `docs/selinux.md` and keep only a one-line pointer in SKILL.md to reduce the monolithic body.

Trim Pro Tips 1–3, which restate Step 4/5 (subvolid=5, highest snapshot = active, /var separate), to avoid redundancy and recover tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands and tables and assumes Claude's competence; the btrfs/transactional-update snapshot model it explains is stack-specific knowledge Claude does not inherently have, so it earns its tokens, with only minor redundancy in Pro Tips restating earlier steps.	3 / 3
Actionability	It provides copy-paste-ready, fully executable commands throughout (hcloud enable-rescue/reboot, mount -o subvolid=5, journalctl -D, sed fixes, chroot ssh-keygen), with concrete examples rather than pseudocode.	3 / 3
Workflow Clarity	Steps 1–7 are clearly sequenced with a diagnostic checklist (5a–5h), Expected/Watch-for checkpoints, a symptom→cause→check→fix table, and a final `ssh ... 'echo ok'` verification after reboot.	3 / 3
Progressive Disclosure	It is a single ~280-line file with well-organized sections but references `docs/selinux.md`, `scripts/destroy.sh`, and `scripts/cleanup.sh` that do not exist as bundle files, and the SELinux/destroy detail that should be split out is inline rather than in clearly signaled one-level-deep references.	2 / 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.

A strong, concise description that pairs an explicit "Use when..." trigger with several concrete diagnostic actions in third-person voice. It clearly states both what the skill does and when to use it with minimal fluff.

Dimension	Reasoning	Score
Specificity	"Boots into rescue mode via hcloud CLI to inspect filesystem, logs, SSH keys, sshd config, and cloud-init state" lists multiple specific concrete actions, matching the anchor for score 3.	3 / 3
Completeness	It explicitly answers both what (boots rescue mode to inspect filesystem/logs/keys/config) and when (an explicit "Use when..." clause), so both are present and clear.	3 / 3
Trigger Term Quality	"Use when a Hetzner node is unreachable, SSH fails, cloud-init seems broken, or provisioning hangs" uses natural symptom terms a user would actually say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	The Hetzner rescue-mode niche with symptom-specific triggers is clearly distinguishable and unlikely to fire for the wrong skill.	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/debug-node/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.