CtrlK
BlogDocsLog inGet started
Tessl Logo

scene-unload

Unload an opened scene from the Unity Editor (asynchronously via `SceneManager.UnloadSceneAsync`). Use 'scene-list-opened' to find the scene name first.

52

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/scene-unload/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-sectioned, actionable tool reference with a concrete, executable CLI invocation and sensible troubleshooting. It loses points for specifying the single input parameter three separate times, using a placeholder value instead of a realistic example, and omitting any validation or caution around the destructive nature of unloading an opened scene.

Suggestions

Collapse the 'Inputs' prose, 'Input' table, and 'Input JSON Schema' into a single specification of the one `name` parameter to cut roughly a third of the body.

Add a validation/caution step — e.g. warn that unloading discards unsaved changes to the scene and suggest confirming the scene name via 'scene-list-opened' before unloading — to lift workflow clarity past the destructive-operation cap.

Replace the `"string_value"` placeholder with a concrete example scene name (e.g. "MainMenu") so the command is copy-paste ready.

DimensionReasoningScore

Conciseness

The single `name` parameter is specified three times — in the 'Inputs' prose, the 'Input' table, and the 'Input JSON Schema' — which is redundant padding beyond the 'minor instances that could be trimmed' anchor 4, though the rest of the body is efficient rather than heavily padded (anchor 2).

3 / 5

Actionability

The body provides a concrete, executable CLI command (`unity-mcp-cli run-tool scene-unload --input '...'`) plus input-file/stdin variants and troubleshooting for the CLI not being found; the minor gap is the literal `"string_value"` placeholder instead of a realistic example, so it fits 'mostly executable with minor gaps' rather than the fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The action itself is unambiguous and the prerequisite (use 'scene-list-opened' first) is stated, but unloading a scene is a destructive operation that discards the scene's in-memory state, and there is no verification step or warning about unsaved changes — per the rubric guideline this caps workflow clarity at 3.

3 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized into clearly signaled sections with its one external pointer ("Read the /unity-initial-setup skill for detailed installation instructions") stated plainly; the minor gaps are the triple-duplicated input spec and the bulky inline output schema that could be consolidated, matching anchor 4's 'good structure ... minor organization gaps'.

4 / 5

Total

14

/

20

Passed

Description

53%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 precise about what the skill does — naming the exact API (`SceneManager.UnloadSceneAsync`) — and occupies a distinct niche. Its main weaknesses are a single covered action and the complete absence of a when-to-use trigger clause with natural synonyms, which caps both completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when the user asks to unload, close, or remove an opened scene in the Unity Editor."

Include natural trigger synonyms (close scene, remove scene, unload scene) so the description matches how users actually phrase the request.

Mention the key behavioral outcome (returns the scene name and an AssetObjectRef to its asset) to round out the capability coverage.

DimensionReasoningScore

Specificity

Names the domain ("Unity Editor") and one concrete action ("Unload an opened scene ... asynchronously via `SceneManager.UnloadSceneAsync`") with the exact API, but only covers a single action, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor above.

3 / 5

Completeness

The 'what' is clear (unload an opened Unity scene asynchronously), but there is no 'Use when...' or equivalent trigger clause; "Use 'scene-list-opened' to find the scene name first" is a prerequisite pointer, not a when-to-use trigger, so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords exist ("unload", "scene", "Unity Editor") but common natural variations users would say — "close scene", "remove scene" — are absent, fitting 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The Unity scene-unloading niche is precise and unlikely to fire for unrelated skills, but with no synonyms and closely related sibling skills (scene-load, scene-list-opened) there is minor overlap risk, matching 'mostly distinct; minor overlap risk' rather than the fully distinct anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.