tests-run

Execute Unity tests (`EditMode` or `PlayMode`) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.

Quality

71%

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 ./Unity-MCP-Plugin/.claude/skills/tests-run/SKILL.md

Quality

Content

67%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 well-structured, actionable, and appropriate for a single-call Unity test runner, with executable CLI examples and a clear domain-reload flow. The main weakness is mild verbosity from triplicated parameter descriptions and placeholder example values.

Suggestions

Collapse the duplicated parameter descriptions: keep either the prose 'Filters'/'Response toggles' sections or the Input table, not both, to save tokens.

Replace placeholder 'string_value' values in the How-to-Call example with one realistic minimal example (e.g. a real testMode and a testClass filter).

Consider moving the verbose output JSON schema (the $defs block) into a references/ file and linking to it, keeping only the top-level shape inline.

Dimension	Reasoning	Score
Conciseness	The prose mostly assumes Claude's competence with no concept filler, but the filter and response-toggle descriptions are restated in both prose and the Input table, and the How-to-Call uses placeholder 'string_value' rather than trimmed real examples.	3 / 5
Actionability	Provides concrete executable commands (run-tool --input, --input-file, stdin pipe) plus troubleshooting fallbacks (npx, global install); only minor gaps from placeholder values in the primary example.	4 / 5
Workflow Clarity	For a single-call wrapper, the sequence is clear with implicit checkpoints (dirty-scene precondition + 'save them and retry', compilation-error short-circuit, Processing/resume across domain reloads), though there is no explicit verify-the-run-completed feedback loop.	4 / 5
Progressive Disclosure	No bundle files exist; the body is well-organized into clearly headed sections with a single one-level-deep pointer to /unity-initial-setup, but the large inline output JSON schema (verbose $defs) could arguably live in a separate reference file.	4 / 5
	Total	15 / 20 Passed

Description

75%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, concrete, and well-targeted to a distinct niche, but it omits an explicit 'when to use' trigger clause, which the rubric penalizes by capping completeness at 3.

Suggestions

Append a 'Use when ...' clause naming natural trigger phrases, e.g. 'Use when the user asks to run Unity tests, check EditMode/PlayMode test results, or filter tests by assembly, namespace, class, or method.'

Add common synonyms a user might say (e.g. 'unit tests', 'test runner', 'run my tests') to broaden trigger-term coverage.

Mention typical file/assembly extensions or naming (e.g. .dll test assemblies) to round out keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — execute Unity tests, return per-test results, filter by assembly/namespace/class/method, refresh AssetDatabase first, defer across domain reloads — covering the skill comprehensively.	5 / 5
Completeness	Clearly states what the skill does but lacks any 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Strong natural terms (Unity tests, EditMode, PlayMode, test assembly, namespace, class, method) match what a user would say, but common synonyms and file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Unity EditMode/PlayMode test execution with layered filters) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: IvanMurzak/Unity-MCP
Path: Unity-MCP-Plugin/.claude/skills/tests-run/SKILL.md
Commit: 07b8f65

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.