CtrlK
BlogDocsLog inGet started
Tessl Logo

assets-create-folder

Create a new folder under a parent folder inside 'Assets/'. The parent path must start with 'Assets/' and every intermediate folder in it must already exist. Refreshes the AssetDatabase at the end and returns the GUID(s) of the created folder(s).

54

Quality

60%

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/assets-create-folder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 well-structured and actionable with real CLI commands and complete schemas, but it opens with redundant restatements of the description and presents validation rules without an explicit sequenced workflow with recovery checkpoints for a batch/destructive operation.

Suggestions

Replace the opening paragraph (which duplicates the frontmatter) with a concise one-line summary and remove the repeated intermediate-folder explanation.

Turn the Validation rules into an explicit ordered workflow (validate inputs -> create per entry -> collect errors -> AssetDatabase.Refresh() -> return GUIDs) with an error-recovery checkpoint, since this is a batch write operation.

Fix the example payload so 'inputs' shows a realistic array of {ParentFolderPath, NewFolderName} objects instead of the literal "string_value" placeholder.

DimensionReasoningScore

Conciseness

The opening paragraph repeats the frontmatter description almost verbatim ('The parent folder string must start with the Assets folder, and all folders within the parent folder string must already exist') and re-explains the intermediate-folder rule already stated in frontmatter, plus a slightly redundant 'Does AssetDatabase.Refresh() at the end. Returns the GUID...' sentence — efficient schema tables but with some padded prose that could be trimmed.

3 / 5

Actionability

It provides concrete, copy-paste-ready CLI commands ('unity-mcp-cli run-tool assets-create-folder --input ...'), stdin piping, a fallback to npx/npm install, and complete input/output JSON schemas; the only gap is the placeholder '"inputs": "string_value"' example which is not a realistic working payload.

4 / 5

Workflow Clarity

Although the skill does batch folder creation with per-entry error collection and a destructive write, the body only lists validation rules in isolation and never sequences them into a validate -> act -> refresh -> return-GUIDs workflow with an explicit error-recovery checkpoint, so it sits at the 'steps listed but validation gaps / checkpoints implicit' anchor; the batch/destructive cap at 3 is satisfied.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (Inputs, Validation, How to Call, Troubleshooting, Input, Output) with schemas inline; no nested references exist and the single cross-skill pointer ('Read the /unity-initial-setup skill') is clearly signaled — minor gap is that the schemas could live in a referenced file, but at this size inline is appropriate.

4 / 5

Total

14

/

20

Passed

Description

62%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 highly specific and clearly scoped to Unity asset-folder creation with concrete preconditions and return values. Its main weakness is the absence of any explicit 'Use when...' trigger guidance, which caps completeness and limits natural trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrasings (e.g. 'Use when organizing scripts and assets in a Unity project, or when the user asks to create folders under Assets/').

Include conversational synonyms alongside technical jargon (e.g. 'folders', 'directory', 'organize assets') so users' natural requests map to the skill.

Rephrase into consistent third-person action voice and consider trimming the slightly redundant restatement of the parent-path rule.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with explicit preconditions and a concrete return value: 'Create a new folder under a parent folder inside Assets/', 'The parent path must start with Assets/', 'every intermediate folder in it must already exist', 'Refreshes the AssetDatabase', 'returns the GUID(s) of the created folder(s)'.

5 / 5

Completeness

It clearly answers 'what' (create folders under existing parent paths in Assets/, refresh AssetDatabase, return GUIDs) but provides no explicit 'when' guidance — there is no 'Use when...' clause or equivalent trigger, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

It uses relevant domain terms ('Assets/', 'AssetDatabase', 'GUID', 'folder') but lacks natural user-facing trigger phrases a person would say (e.g. 'organize assets', 'create Unity folders'); the vocabulary is technical Unity jargon rather than conversational triggers, and it omits the 'Use when...' phrasing that anchors the top of the scale.

3 / 5

Distinctiveness Conflict Risk

The 'Assets/' + 'AssetDatabase' + 'GUID' niche is clearly Unity-specific and distinct from generic file skills, with only minor overlap risk against other Unity asset skills; it lacks a fully explicit trigger clause so it does not reach 5.

4 / 5

Total

15

/

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.

Validation16 / 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.