test-changes

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

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/test-changes/SKILL.md

Quality

Content

81%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 body is a highly actionable, well-sequenced runbook with strong validation checkpoints, checklists, and error-recovery guidance. Its weaknesses are mild over-explanation in a few rationale paragraphs and a monolithic structure that could offload some detail to reference files.

Suggestions

Tighten the tangential rationale paragraphs (Empty-State Upgrade Gotcha, CI render-harness Lint history, teardown autoscaler note) to the essential operational guidance to improve conciseness.

Consider moving the detailed Teardown, CI Truth-Checking, and Common Issues sections into one-level-deep reference files (e.g. TEARDOWN.md) so the main SKILL.md stays a lean overview.

The lower score is conciseness; review each multi-paragraph explanation and trim anything not needed for Claude to execute or decide correctly.

Dimension	Reasoning	Score
Conciseness	The body is mostly direct commands but includes several multi-paragraph rationales that pad beyond the essential (the Empty-State Upgrade Gotcha, the CI render-harness Lint history, and the teardown autoscaler digression), matching 'mostly efficient but includes some unnecessary explanation'; it avoids explaining basic concepts Claude already knows so it is not a 2.	3 / 5
Actionability	Every step gives copy-paste-ready bash with real flags (e.g. 'terraform init -backend=false', the rsync temp-copy block), and the Quick Reference composes the full executable sequence; environment-specific values are clearly signaled placeholders, matching 'fully executable; copy-paste ready'.	5 / 5
Workflow Clarity	Nine steps are explicitly sequenced with a graphviz flow diagram, each gated by 'Must pass before proceeding', plus a Step 9 checklist, a Red Flags STOP! table, and Common Issues recovery guidance — clear sequence, explicit validation, feedback loops, and a checklist matching the top anchor.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Overview, Workflow, Steps 1-9, Quick Reference, Common Issues) with no nested references, but it is a ~340-line monolithic file with no one-level-deep reference split, so it sits at 'good structure; minor organization gaps' rather than the clean overview-pointing-to-references anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

78%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 specific and well-triggered, clearly naming the domain and three core actions with an explicit 'Use after making changes' clause. It is strong on distinctiveness; the main weakness is the generic 'when' that does not specify Terraform/OpenTofu changes.

Dimension	Reasoning	Score
Specificity	Quotes 'run Terraform/OpenTofu formatting, validation, and plans' name the domain plus three concrete actions; matches the anchor listing several specific actions with minor gaps, falling short of comprehensive coverage (the body's nine sub-checks are not enumerated).	4 / 5
Completeness	It has a clear 'what' (formatting/validation/plans against test environment) and an explicit 'when' trigger clause ('Use after making changes'), but the 'when' is generic about which changes, so it matches 'both what and when; when could be more specific' rather than the concrete multi-trigger anchor 5.	4 / 5
Trigger Term Quality	Natural terms a user would say are present — 'Terraform/OpenTofu', 'formatting', 'validation', 'plans', 'test environment' — giving good keyword coverage, though a few natural synonyms (lint, apply, .tf/hcl) are absent so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'Terraform/OpenTofu ... test environment', a clear niche with distinct triggers and minimal overlap risk, matching the anchor for a distinct specialized skill.	5 / 5
	Total	17 / 20 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: 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.