scene-get-data

Retrieve the list of root GameObjects in the specified opened scene (or the active scene when `openedSceneName` is empty). Supports token-saving path-scoped reads over the root-GameObjects array via `paths` or `viewQuery`. Use 'scene-list-opened' to enumerate scenes.

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-get-data/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 a solidly structured tool reference: the invocation is fully executable, parameters and output schema are documented, and edge handling (stdin, npx fallback) is addressed. Its weaknesses are redundancy (path syntax stated three times) and a monolithic inlining of large JSON schemas that should live in separate reference files given the skill's ~430-line size.

Suggestions

Move the Input/Output JSON schemas into a references/ file (e.g. references/schema.md) and keep only the parameter table plus one runnable example inline.

Consolidate the path-syntax explanation into a single section; the `paths` table row and ViewQuery.Path description repeat it nearly verbatim.

Add a realistic end-to-end example (e.g. scene 'Main.unity' with paths ["[0]/name"]) and a note to check `IsValidScene`/`IsLoaded` when a scene name is supplied.

Dimension	Reasoning	Score
Conciseness	Path syntax is explained three times (the 'Path syntax' section, the `paths` input-table row, and the ViewQuery.Path schema description), and ~290 lines of auto-generated output JSON schema are inlined. It is mostly efficient — it does not explain concepts Claude already knows — but the duplication and schema bulk could be trimmed.	3 / 5
Actionability	Provides the exact CLI command with full JSON input, `--input-file`/stdin alternatives, and CLI-not-found troubleshooting — concrete and executable. Held at 4 rather than 5 because the examples use placeholders ('string_value') instead of a realistic ready-to-run invocation; only one concrete path example ('[0]/name') is given.	4 / 5
Workflow Clarity	As a read-only single-action tool skill, the action is unambiguous: one fully documented CLI call with mutually-exclusive parameters called out. Minor validation gap — no guidance to check `IsValidScene`/`IsLoaded` in the result when a scene name was supplied, and the troubleshooting is reactive only.	4 / 5
Progressive Disclosure	Sections are well-organized (Toggles, Path-scoped reads, How to Call, Input, Output) with no nested references, but there are no bundle files — the large input/output JSON schemas are inlined in SKILL.md where they clearly belong in separate reference files (e.g. references/output-schema.md).	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.

A concrete, well-scoped third-person description that names the tool's capability precisely and cross-references the sibling scene-listing tool. Its main weakness is the absent 'Use when…' trigger clause, which caps completeness and slightly weakens trigger-term utility.

Suggestions

Add an explicit trigger clause, e.g. 'Use when inspecting a Unity scene's hierarchy, reading root GameObjects, or fetching scene contents before modifying objects.'

Include a natural synonym or two ('scene hierarchy', 'Unity scene') to improve trigger-term coverage.

Briefly mention the includeRootGameObjects/includeBounds/includeData toggles so the described capability matches what the tool offers.

Dimension	Reasoning	Score
Specificity	Quotes several concrete actions in third person — 'Retrieve the list of root GameObjects in the specified opened scene' and 'token-saving path-scoped reads over the root-GameObjects array via `paths` or `viewQuery`'. Minor gaps in coverage (the includeRootGameObjects/includeBounds/includeData toggles are unmentioned) keep it below the comprehensive 5 anchor.	4 / 5
Completeness	The 'what' is clear (retrieve root GameObjects of a scene, with path-scoped reads), but there is no 'Use when…' or equivalent explicit trigger guidance — the 'Use scene-list-opened to enumerate scenes' sentence points to a sibling tool, not when to use this one. Per the judging guidelines this caps completeness at 3.	3 / 5
Trigger Term Quality	Natural Unity vocabulary is present ('root GameObjects', 'opened scene', 'active scene'), which a user would plausibly say. A few natural synonyms are missing ('hierarchy', 'inspect scene', 'Unity'), so it does not reach comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (root GameObjects of a scene) and explicitly differentiates from 'scene-list-opened' for scene enumeration. Minor overlap risk remains with sibling GameObject-inspection tools in the same tool family.	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-get-data/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.