scene-create

Create a new Unity scene asset and save it at the given `.unity` path. Use 'scene-list-opened' to inspect the resulting opened-scene set afterwards.

Quality

72%

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/scene-create/SKILL.md

Quality

Content

63%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 actionable and the single-step workflow is clear with a stated verification follow-up, but it is held back by duplicated parameter documentation and a large inlined API schema. Merging the two input sections and moving schemas to a reference file would lift both conciseness and structure.

Suggestions

Merge the "## Inputs" prose section and the "## Input" table into one section to remove the duplicated parameter documentation.

Move the input/output JSON schemas to a references/ file (e.g., references/schemas.md) and keep only the essential fields inline.

Replace the "string_value" placeholders in the example with a realistic filled-in call, e.g., a path like "Assets/Scenes/Main.unity".

Dimension	Reasoning	Score
Conciseness	The "## Inputs" prose section and the later "## Input" table document the same three parameters twice, the scene-list-opened suggestion repeats the frontmatter description verbatim, and the output schema carries long Unity-doc text (e.g., the IsValidScene explanation). The CLI/schema content itself is efficient, so this is mostly efficient with clear tightening opportunities rather than severely padded.	3 / 5
Actionability	"unity-mcp-cli run-tool scene-create --input '{...}'" plus the --input-file and stdin variants and the npx troubleshooting note are concrete and executable. It stops short of 5 because the example uses "string_value" placeholders instead of a realistic filled-in call, so it is not literally copy-paste ready.	4 / 5
Workflow Clarity	The single action is unambiguous: Behavior states it calls EditorSceneManager.NewScene + SaveScene on the main thread and returns SceneDataShallow, and a post-call verification step is stated ("Use 'scene-list-opened' to inspect the resulting opened-scene set afterwards"). Not a destructive or batch operation, so no validation cap applies; it misses 5 only because no guidance covers failure handling (e.g., invalid path or existing scene).	4 / 5
Progressive Disclosure	Sections are clearly headed (Inputs, Behavior, How to Call, Troubleshooting, Input, Output), but no bundle files exist and roughly 90 lines of input/output JSON schemas are inlined in the body — reference material that would sit better in a separate file. The skill is over 50 lines, so the small-skill exception for a 5 does not apply.	3 / 5
	Total	14 / 20 Passed

Description

66%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, distinct, and uses natural trigger terms well, but it never states when the skill should be used. Adding an explicit "Use when creating new scenes or setting up a scene file" clause would raise completeness from 3 to 5.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user wants to create a new scene, set up a scene file, or add a .unity asset to the project."

Optionally mention the two creation modes (empty scene vs. default game objects) to strengthen the 'what' coverage.

Include one or two common synonyms such as "new scene" or "additive scene" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Create a new Unity scene asset and save it at the given `.unity` path" names the domain and concrete actions (create, save at a specific path), which is comprehensive for a single-purpose tool. It falls short of a 5 only because it omits the optional setup/mode behaviors the tool actually supports.	4 / 5
Completeness	The "what" is clearly stated (create and save a Unity scene at a given path), but there is no "Use when..." clause or equivalent explicit trigger guidance — the 'scene-list-opened' sentence describes a follow-up action, not when to invoke this skill. Per the judging guideline, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms users would say are present: "Unity", "scene", "create", and the ".unity" file extension. A few plausible synonyms (e.g., "new scene", "level", "add scene") are missing, keeping it below the comprehensive-synonym coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The ".unity" path and scene-asset framing give it a clear niche with minimal conflict risk against non-Unity skills. Minor overlap remains with closely related sibling scene skills (scene-open, scene-save), since "create a scene" phrasing alone doesn't fully separate them.	4 / 5
	Total	15 / 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/scene-create/SKILL.md
Commit: 4c8056f

Reviewed: 9 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.