scene-open

Open a Unity scene asset in Single or Additive mode. Returns the post-open list of all opened scenes. Use 'assets-find' to locate the scene asset first.

Quality

62%

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-open/SKILL.md

Quality

Content

48%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 delivers a clear two-step workflow and complete parameter/schema information, but suffers from triple-duplicated input documentation, inconsistent section structure, and placeholder-only examples. Moving the schemas to a reference file and consolidating the input documentation would materially improve it.

Suggestions

Consolidate the "## Inputs" prose, "## Input" table, and JSON schema into a single source of truth — keep the concise prose list and move the full JSON schemas to a references/ file.

Replace the "string_value" placeholders with a copy-paste-ready worked example, e.g. a sceneRef using "assetPath": "Assets/Scenes/Main.unity".

Fix the internal inconsistencies: document (or remove) the "AdditiveWithoutLoading" enum value, reconcile the sceneRef type ("any" vs "AssetObjectRef"), and unify heading levels and names.

Dimension	Reasoning	Score
Conciseness	The same inputs are documented three times — the "## Inputs" prose list, the "## Input" table, and the ~100-line inlined JSON schema — plus generic CLI stdin/pipe boilerplate; roughly 60 lines are redundant padding, matching anchor 2.	2 / 5
Actionability	The CLI command shape is real ("unity-mcp-cli run-tool scene-open --input '{...}'") but uses "string_value" placeholders instead of a worked example with an actual sceneRef (assetPath or instanceID), so it is not copy-paste ready — matching anchor 3's incomplete concrete guidance.	3 / 5
Workflow Clarity	The flow is clear and single-purpose (find the asset via 'assets-find', then run the tool) with throw conditions stated; minor gaps remain — the schema's "AdditiveWithoutLoading" enum value is undocumented and the two input sections contradict each other (type "any" vs "AssetObjectRef").	4 / 5
Progressive Disclosure	Section headers exist but are inconsistent ("## Inputs" vs "## Input", "### Troubleshooting" nested under "How to Call" while others are top-level), and the large JSON schemas are inlined in SKILL.md rather than split into a reference file — matching anchor 3.	3 / 5
	Total	12 / 20 Passed

Description

58%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.

A concise, concrete description that clearly states what the tool does and how to prepare its input. Its main weakness is the absence of a "Use when..." trigger clause and of natural trigger variations ("load scene", ".unity"), which limits discoverability and completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to open or load a Unity scene, switch scenes, or add a scene additively."

Include natural synonyms and file extensions users would say, such as "load scene", "additive scene load", and ".unity scene files".

Consider naming the return contract in user-facing terms (e.g. "returns the list of currently opened scenes with load/validity state") to further sharpen distinctiveness from sibling scene tools.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "Open a Unity scene asset in Single or Additive mode", "Returns the post-open list of all opened scenes", "Use 'assets-find' to locate the scene asset first" — with only minor gaps in coverage of the tool's surface, matching anchor 4 rather than the comprehensive anchor 5.	4 / 5
Completeness	The "what" is clear (open a scene in Single or Additive mode, get back the opened-scenes list) but there is no "Use when..." trigger clause; "Use 'assets-find' to locate the scene asset first" states a prerequisite, not when to invoke the skill, so completeness is capped at 3.	3 / 5
Trigger Term Quality	Relevant keywords like "Unity", "scene", "open", "Single", "Additive" are present, but common variations users would naturally say — "load scene", "additively", ".unity" file extension — are missing, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	"Open a Unity scene asset in Single or Additive mode" carves a clear niche with distinct triggers; only minor overlap risk with closely related sibling tools (scene-close, scene-save, scene-load).	4 / 5
	Total	14 / 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-open/SKILL.md
Commit: 4c8056f

Reviewed: 8 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.