test-changes

Use after making changes to run Terraform/OpenTofu formatting, validation, and plans against the test environment

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

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.

A highly actionable, clearly sequenced validation workflow with strong validation checkpoints, but it is monolithic and somewhat redundant. Splitting peripheral material (teardown, CI, AI-review) into reference files and de-duplicating the repeated sequence would improve token efficiency and progressive disclosure.

Suggestions

Remove the redundancy between the workflow digraph, the per-step bash blocks, and the Quick Reference — keep the numbered steps and link the Quick Reference as a one-block summary rather than repeating all commands.

Move teardown procedures, CI truth-checking, Common Issues, and AI-Assisted Review into separate reference files (e.g. references/teardown.md, references/ci.md) and signal them from SKILL.md to improve progressive disclosure.

Trim or drop the AI-Assisted Review section, which is tangential to the core fmt/validate/plan task and adds tokens that do not earn their place.

Dimension	Reasoning	Score
Conciseness	Content is dense and operational with no basic-concept padding, but the test sequence is triple-repeated (workflow digraph, numbered steps, and Quick Reference) and the AI-Assisted Review section is tangential, so it could be tightened rather than earning the lean level-3.	2 / 3
Actionability	Fully executable, copy-paste bash blocks throughout every step; the single placeholder (<existing-cluster-terraform-root>) is explicitly operator-supplied, matching the 'fully executable / copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps 1–9 are explicitly sequenced, each gated with 'Must pass before proceeding', plus a red-flags STOP table, breaking-change feedback loop, and a final checklist — matching the 'clear sequence with explicit validation steps and checklists' anchor.	3 / 3
Progressive Disclosure	Sections are well-organized, but the ~340-line body is monolithic with no external references, and teardown/CI/common-issues/AI-review content that could live in separate files is inline; it exceeds the 'under 50 lines' carve-out that would allow a 3.	2 / 3
	Total	10 / 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 concise, well-targeted description that states concrete actions, an explicit use-trigger, and a distinct niche without fluff or over-claiming. It cleanly satisfies all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions ("formatting, validation, and plans") on a specific toolset (Terraform/OpenTofu), matching the 'multiple specific concrete actions' anchor rather than the domain-only level 2.	3 / 3
Completeness	Explicitly answers both what (run formatting, validation, and plans against the test environment) and when ("Use after making changes"), satisfying the explicit-trigger requirement that avoids the level-2 cap.	3 / 3
Trigger Term Quality	Natural terms a user would say are well covered — "Terraform", "OpenTofu", "formatting", "validation", "plans", "test environment" — going beyond a single keyword toward the natural-vocabulary level 3 anchor.	3 / 3
Distinctiveness Conflict Risk	Scoped to Terraform/OpenTofu test-environment validation, a clear niche with distinct triggers unlikely to fire for unrelated skills; not generic enough to fall to level 2.	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: 11 missing	Warning

	Total	15 / 16 Passed

Repository: mysticaltech/terraform-hcloud-kube-hetzner
Path: .claude/skills/test-changes/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.