scene-save

Save an opened scene back to its asset file (or to a new path when `path` is provided). When `openedSceneName` is empty, saves the currently active scene. Use 'scene-list-opened' to find the scene name first.

Quality

70%

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-save/SKILL.md

Quality

Content

67%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 fully executable CLI guidance with a real validation/error-handling section, which is appropriate for this simple single-purpose tool. Its main flaws are redundancy — the same two parameters documented three times in differently named sections — and placeholder-only examples with no worked invocation.

Suggestions

Merge the "## Inputs", "## Input" table, and "### Input JSON Schema" into one section (the table alone suffices; drop the schema or the bullets) and use a consistent section name.

Replace the "string_value" placeholders with one worked example, e.g. --input '{"openedSceneName": "Main", "path": "Assets/Scenes/Main_v2.unity"}', so both the active-scene and save-as cases are demonstrated.

Promote "### Troubleshooting" to a top-level section or fold it into "How to Call" so heading levels reflect the document structure.

Dimension	Reasoning	Score
Conciseness	The two parameters are presented three times ("## Inputs" bullets, "## Input" table, "### Input JSON Schema") and the intro restates the frontmatter description, so the content could be tightened. It avoids anchor 2 because there is no padding that explains concepts Claude already knows.	3 / 5
Actionability	The "How to Call" section gives executable CLI commands in three forms (`--input '{...}'`, `--input-file args.json`, stdin heredoc) and troubleshooting supplies `npm install -g` / `npx` alternatives. It misses anchor 5 only because the examples use "string_value" placeholders with no worked, filled-in example or sample output.	4 / 5
Workflow Clarity	The single save action is unambiguous, and the "## Validation" section documents thrown error conditions plus that SaveScene failure "surfaces an error with the current opened-scenes list for diagnosis" — a genuine feedback signal. It is below anchor 5 because there is no explicit post-save verification step, though the documented validation behavior avoids the destructive-operation cap of 3.	4 / 5
Progressive Disclosure	With no bundle files, everything appropriately lives in a short, headered SKILL.md and the only external pointer ("Read the /unity-initial-setup skill") is one level deep and clearly signaled. The duplicated "## Inputs" vs "## Input" sections with inconsistent naming, and the oddly nested "### Troubleshooting", keep it from anchor 5.	4 / 5
	Total	15 / 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.

The description is concrete and precise about the save operation and its parameter semantics, with a useful cross-reference to scene-list-opened. Its main weaknesses are the absent "Use when..." trigger clause (capping completeness at 3) and missing natural terms like "Unity" and ".unity" that would improve both trigger quality and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to save a Unity scene, persist scene changes, or save a scene to a new .unity path."

Mention "Unity" and the ".unity" file extension in the description to improve natural-keyword coverage and reduce conflict with other scene-related skills.

Include the common phrasing "save as" for the new-path variant so it matches how users naturally express that request.

Dimension	Reasoning	Score
Specificity	The description lists several concrete, parameter-conditioned behaviors ("Save an opened scene back to its asset file (or to a new path when `path` is provided)", "saves the currently active scene") rather than vague language. It sits below anchor 5 because all behaviors are facets of a single save operation rather than comprehensive multi-action coverage.	4 / 5
Completeness	The "what" is clear and detailed, but there is no "Use when..." clause or equivalent explicit trigger guidance; "Use 'scene-list-opened' to find the scene name first" is a prerequisite pointer, not a when-to-use trigger. Per the judging guidelines, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords like "save", "opened scene", "active scene", and "asset file" are present, but common variations users would naturally say are missing — notably "Unity", the ".unity" extension, and "save as" phrasing. This matches anchor 3 (some relevant keywords, missing common variations) better than anchor 4's fuller coverage.	3 / 5
Distinctiveness Conflict Risk	The description carves a clear niche within its tool family (save vs. list/open), anchored by "asset file" and the explicit 'scene-list-opened' reference. It falls short of anchor 5 because the generic word "scene" without "Unity" leaves minor overlap risk with other scene-related skills.	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-save/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.