scene-list-opened

List every scene currently opened in the Unity Editor as a shallow snapshot (name, path, build flags). Use 'scene-get-data' for the deep view of a specific scene.

Quality

77%

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-list-opened/SKILL.md

Quality

Content

73%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.

A well-structured, executable single-tool reference with clear invocation, troubleshooting, and I/O documentation. Its main weaknesses are token redundancy (duplicated input table/schema, verbatim Unity API quotes, generic CLI boilerplate) and placeholder values that don't reflect the tool's real no-argument invocation.

Suggestions

Drop either the Input table or the Input JSON Schema (they duplicate each other), and trim the verbatim Unity documentation quote inside IsValidScene to a one-line summary.

Replace the placeholder inputs ("nothing": "string_value") with the tool's actual invocation — an empty object '{}' — since the parameter is optional and unused.

Condense the generic input-file/stdin boilerplate to one line (e.g. "For complex input, use --input-file args.json or pipe via stdin"), or move the output schema detail to a reference file if this skill grows.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes avoidable bulk: the Input table and Input JSON Schema duplicate the same (empty) parameter information, the IsValidScene property embeds a long verbatim Unity API documentation quote, and the generic input-file/stdin boilerplate pads the How to Call section — matching anchor 3 rather than 4.	3 / 5
Actionability	"unity-mcp-cli run-tool scene-list-opened --input '{...}'" is a concrete, executable command with npx fallback and troubleshooting, but the placeholder inputs ("nothing": "string_value", {"param": "value"}) are generic rather than reflecting the tool's actual no-parameter call, a minor gap that keeps it at anchor 4 instead of 5.	4 / 5
Workflow Clarity	This is a simple single-task skill — run one CLI command — and the single action is unambiguous, with a Troubleshooting section providing an error-recovery path (install globally or use npx), so the simple-skill exception applies and the workflow merits 5 rather than 4.	5 / 5
Progressive Disclosure	Sections (Behavior, How to Call, Troubleshooting, Input, Output) are well organized with no nested references, and no bundle files exist, so the single-file structure is appropriate; the ~70-line inline output JSON schema with embedded Unity documentation is inline content that could live in a reference file, a minor organization gap that keeps this at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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 crisp, concrete description with excellent distinctiveness and good trigger terms, weakened by the absence of any 'Use when...' trigger clause, which caps completeness at 3. Adding explicit trigger guidance would move it to the top tier.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks which scenes are open, what scene is loaded, or wants scene names/paths/build indices in the Unity Editor."

Include natural synonyms or file extensions users might mention, such as ".unity" files, "active scene", or "scene hierarchy", to broaden trigger coverage.

Consider briefly noting when this shallow view suffices versus when scene-get-data is needed to strengthen the boundary guidance into actionable trigger guidance.

Dimension	Reasoning	Score
Specificity	"List every scene currently opened in the Unity Editor as a shallow snapshot (name, path, build flags)" names the domain and a concrete action with enumerated output fields, but describes only one action rather than multiple, matching anchor 4 rather than 5.	4 / 5
Completeness	The description has a clear 'what' (list opened scenes with name, path, build flags) but no 'Use when...' clause or equivalent trigger guidance; the 'Use scene-get-data for the deep view' sentence is boundary guidance, not a when-to-use trigger, so completeness is capped at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	"scene", "Unity Editor", "opened", and "list" are natural terms a user would say, giving good keyword coverage, but common variations like ".unity", "active scene", or "hierarchy" are missing, so it falls short of anchor 5 and above anchor 3's 'missing common variations'.	4 / 5
Distinctiveness Conflict Risk	"List every scene currently opened in the Unity Editor as a shallow snapshot" carves out a clear niche, and the explicit redirection to 'scene-get-data' for the deep view distinguishes it from its closest sibling skill, giving minimal conflict risk.	5 / 5
	Total	16 / 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-list-opened/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.