kh-assistant

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

Quality

72%

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

71%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.

The content is highly actionable with executable commands, templates, and validation-gated workflows, and is well structured by section. Its weaknesses are conciseness (significant length with some repetition) and progressive disclosure (no bundle files, so detail that should live in separate references is inlined).

Suggestions

Move the Common Issues Catalog and Configuration Templates into separate bundle files (references/issues.md, references/templates.tf) and link one level deep, reducing the main file's token footprint.

De-duplicate the repeated 'fetch latest release' and sibling-skill routing guidance into a single authoritative section to tighten conciseness.

Promote the inlined Hetzner server-type/location tables to a references/hetzner.md file, keeping only the minimum needed for quick routing in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material (tables of variables, errors, server types) but runs ~800 lines with some redundancy (the latest-release fetch and routing rules repeat across sections) and could be tightened; it assumes Claude's competence but is larger than needed for an overview.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash/terraform blocks throughout (gh release list, terraform fmt/validate/plan, complete kube.tf templates, destroy.sh workflows) covering the common cases with specific commands and values.	5 / 5
Workflow Clarity	Workflows (Debugging, Teardown, Upgrades, Migration) are clearly numbered with explicit validation checkpoints (terraform plan for destructions, the hcloud no-destroy gate, 'Only when valid' steps), though the multi-skill routing adds branching that slightly muddies the primary flow.	4 / 5
Progressive Disclosure	Content is section-organized with many references to repo files (docs/llms.md, MIGRATION.md, examples/*.tf.example), but no bundle files exist in this skill so all detail is inlined in one ~800-line SKILL.md; the catalog and templates clearly belong in separate files but are not split out.	3 / 5
	Total	15 / 20 Passed

Description

73%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.

The description is well-structured with an explicit 'Use when' trigger and a clear product niche, but the 'what' is stated abstractly ('intelligent assistant with live repo access') rather than as concrete enumerated capabilities. Specificity is the main weakness; trigger quality and completeness are solid.

Suggestions

Replace the abstract 'acts as an intelligent assistant with live repo access' with 2-3 concrete capabilities (e.g., 'generate kube.tf configs, diagnose cluster errors, recommend v3 topologies') to lift specificity.

Add natural synonyms users might say (e.g., 'Terraform kube-hetzner module', 'Hetzner k3s/RKE2 cluster') to broaden trigger coverage beyond the single product name.

Dimension	Reasoning	Score
Specificity	Names the domain (kube-hetzner configuration, debugging, questions) and two concrete action categories ('configuration, debugging'), but actions are generic and not comprehensive; no enumeration of specific actions like generate kube.tf, diagnose errors, or recommend topologies.	3 / 5
Completeness	Explicitly answers 'when' ('Use when users need help with...') and gives a clear 'what' ('acts as an intelligent assistant with live repo access'), but the 'what' is slightly abstract ('intelligent assistant') rather than a precise capability list.	4 / 5
Trigger Term Quality	'Use when users need help with kube-hetzner configuration, debugging, or questions' provides good keyword coverage of natural trigger phrases, though it lacks synonyms or file-extension style variations and relies on a single product name.	4 / 5
Distinctiveness Conflict Risk	The single explicit product trigger 'kube-hetzner' carves out a clear niche with minimal overlap risk against generic skills; the routing-to-sibling-skills design further isolates its scope.	5 / 5
	Total	16 / 20 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 (809 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: 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.