test-setup

Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow. Run once during Technical Setup phase before the first sprint begins.

Quality

75%

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/test-setup/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable scaffolding skill with real, executable templates and a clear phased workflow, but it is a monolithic single file with some motivational padding and no post-creation verification step.

Suggestions

Add a Phase 5.5/6 verification step that confirms the scaffold works — e.g., lint the tests.yml YAML and run the engine's test runner once against a sample test — to introduce a feedback loop for the batch creation.

Split the per-engine details (Godot/Unity/Unreal runner code and CI YAML) into reference files such as references/engines/godot.md and link to them one level deep, leaving SKILL.md as a lean overview.

Trim motivational framing like 'A test framework installed at sprint start costs 30 minutes... costs 3 sprints' and the opening paragraph that restates the description to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete templates and instructions, but includes motivational padding ('A test framework installed at sprint start costs 30 minutes... costs 3 sprints'), restates the description, and has prose that could be tightened — efficient but not lean enough for a 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready artifacts — real GDScript in gdunit4_runner.gd, complete GitHub Actions YAML for all three engines, and concrete commands like 'godot --headless --script tests/gdunit4_runner.gd' — rather than pseudocode.	3 / 3
Workflow Clarity	The 6-phase sequence is clear with an engine-config guard/redirect and an approval gate, but this batch file-creation workflow lacks a post-creation validation/verification step, capping it at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	No bundle files exist and the ~400-line skill keeps all three engine blocks (runner code + CI YAML) inline; it is well-sectioned but content that could be split into per-engine references is inline, and there are no one-level-deep references.	2 / 3
	Total	9 / 12 Passed

Description

85%

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, specific description that conveys concrete capabilities and an explicit use-when clause with low conflict risk. Its only weakness is moderate trigger-term coverage that mixes in project-specific jargon and skips common variations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow' — matching the multi-action score-3 anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Clearly answers both 'what' (scaffold test framework + CI/CD, directory structure, runner config) and 'when' via the explicit trigger 'Run once during Technical Setup phase before the first sprint begins', so it is not capped at 2 for missing trigger guidance.	3 / 3
Trigger Term Quality	'test framework', 'CI/CD pipeline', and 'GitHub Actions workflow' are natural terms, but it leans on project jargon ('Technical Setup phase', 'sprint') and omits common variations like 'testing' or 'automated tests', so it stops short of full coverage.	2 / 3
Distinctiveness Conflict Risk	The engine-specific test-scaffolding niche combined with CI/CD and the 'Technical Setup phase' framing gives a distinct trigger profile unlikely to collide with general skills.	3 / 3
	Total	11 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/test-setup/SKILL.md
Commit: 984023d

Reviewed: 3 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.