kh-assistant

Use when users need help with kube-hetzner configuration, debugging, or questions - acts as an intelligent assistant with live repo access

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/kh-assistant/SKILL.md

Quality

Content

77%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.

An exceptionally actionable and well-sequenced operational guide with concrete commands, templates, and validated destructive-workflow checkpoints, weakened mainly by length/ redundancy and the absence of any bundle-file split for its large reference material.

Suggestions

De-duplicate the repeated "latest release" gh command by centralizing it once and cross-referencing it from the workflows.

Move the server-type, location, and config-template tables into a references/ file (e.g. references/config-templates.md) and keep SKILL.md as an overview that links to it, improving progressive disclosure.

Relocate the "v3.0.1" baseline and "pricing 2026" time-sensitive facts into a clearly marked version/baseline section so stale values are easy to update.

Dimension	Reasoning	Score
Conciseness	The ~790-line body is content-dense with project-specific facts Claude does not already know (variable names, error patterns, v3.0.0/#2236 regressions), but it repeats commands across sections (the latest-release gh command appears four times) and embeds time-sensitive info ("v3.0.1" baseline, "pricing 2026") outside a deprecated section, so it could be tightened.	2 / 3
Actionability	It provides fully executable commands (gh release list, terraform fmt/validate/plan, scripts/destroy.sh -auto-approve) and complete copy-paste Terraform templates (minimal dev, production HA, private+NAT, Cilium, ARM, super-HA) with exact variable names and syntax.	3 / 3
Workflow Clarity	The numbered workflows (kube.tf, debugging, teardown, upgrades, v2→v3) are clearly sequenced, and the destructive teardown and upgrade flows include explicit validation checkpoints and feedback loops (terraform plan -out, the protected no-destroy gate, "Do not apply when the plan has unexplained replacements or destroys").	3 / 3
Progressive Disclosure	The body is well-sectioned with clear headers and one-level pointers to repo files (docs/llms.md, MIGRATION.md) and sibling skills, but no bundle files exist and the large inline server-type tables, full config templates, and common-issues catalog could be split into separate reference files, leaving the overview monolithic.	2 / 3
	Total	10 / 12 Passed

Description

75%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 focused, third-person description with an explicit Use-when trigger and a clear niche, but its action vocabulary is generic and it lacks the natural term variations (k3s, RKE2, Hetzner, terraform-hcloud-kube-hetzner) users actually utter.

Suggestions

Replace the generic action buckets ("configuration, debugging, or questions") with concrete actions such as "generate kube.tf configs, diagnose plan errors, upgrade k3s/RKE2 clusters, and migrate v2 to v3".

Expand trigger terms to the variations users say: "kube-hetzner", "terraform-hcloud-kube-hetzner", "Hetzner k3s/RKE2 cluster", "kube.tf".

Dimension	Reasoning	Score
Specificity	Names the kube-hetzner domain and three action buckets ("configuration, debugging, or questions") plus "acts as an intelligent assistant with live repo access", but the actions are generic activity categories rather than the multiple concrete, distinct actions the top anchor requires.	2 / 3
Completeness	It explicitly answers both what ("acts as an intelligent assistant with live repo access") and when (an explicit "Use when..." trigger clause), and the guideline caps completeness at 2 only when the trigger guidance is missing — it is present here.	3 / 3
Trigger Term Quality	The "Use when users need help with kube-hetzner configuration, debugging, or questions" clause uses natural terms, but it omits common variations a user would actually say (terraform-hcloud-kube-hetzner, k3s, RKE2, Hetzner cluster), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	It targets the single named project kube-hetzner with distinct, project-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (799 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/kh-assistant/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.