assets-get-data

Get asset data from the asset file in the Unity project — every serializable field and property. Supports token-saving path-scoped reads via `paths` or `viewQuery`. Use 'assets-find' to find the asset first.

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/assets-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 provides fully executable CLI guidance with useful troubleshooting and explicit parameter semantics, and it stays lean in prose. Its main weaknesses are redundancy (duplicated intro and thrice-repeated path syntax) and inlining of the two full JSON schemas that would be better placed in reference files.

Suggestions

Replace the placeholder values in the 'How to Call' example with a realistic worked example (e.g., an actual assetRef, a paths array, and a viewQuery) so it is copy-paste runnable.

Move the Input/Output JSON schemas into references/ files (e.g., references/input-schema.md and references/output-schema.md) and keep only the parameter table inline, reducing SKILL.md to an overview.

Remove the duplicated intro sentence and state the path syntax once (in the 'Path syntax' section), dropping it from the input table row.

Dimension	Reasoning	Score
Conciseness	The prose is lean and assumes Claude's competence (no explaining what Unity or JSON is), but the intro paragraph repeats the frontmatter description almost verbatim, path syntax is stated three times (dedicated section, input table, and again in ViewQuery schema descriptions), and ~130 lines of JSON schemas are inlined. Matches 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Concrete, runnable CLI commands are given (run-tool with --input, --input-file, and stdin heredoc variants) plus troubleshooting for a missing binary. Not 5 because the example uses placeholder "string_value" for every parameter instead of a realistic worked example with actual values.	4 / 5
Workflow Clarity	This is a single-tool, read-only skill: the prerequisite (find the asset with 'assets-find' first) and the single call are unambiguous, and the mutually-exclusive paths/viewQuery options are explicitly stated, so no validation checkpoint is needed for a non-destructive read. Minor gap: no end-to-end example with real values showing the find-then-read flow.	4 / 5
Progressive Disclosure	The single SKILL.md is well-sectioned with clear headers, but there are no bundle files (no references/, scripts/, or assets/ directories) and the two large JSON schemas (~130 lines combined) are inlined rather than split into reference files. At ~190 lines this exceeds the under-50-line simple-skill exception, matching 'some structure but content that should be separate is inline'.	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.

The description is specific and domain-anchored with concrete parameter-level capabilities and mostly natural trigger terms, but it lacks any explicit 'when to use' trigger clause, capping its completeness. It is clearly distinct from its sibling skill. Voice is third person, as required.

Suggestions

Add an explicit trigger clause, e.g., "Use when you need to inspect or read values from a Unity asset (Material, ScriptableObject, Prefab) found via assets-find."

Include natural synonyms and concrete asset-type keywords (prefab, material, scriptable object, inspector values) to broaden trigger coverage.

Clarify what 'asset data' means in the when-clause context so users searching for 'read Unity asset values' match naturally.

Dimension	Reasoning	Score
Specificity	Quotes like "Get asset data from the asset file in the Unity project — every serializable field and property" and "path-scoped reads via `paths` or `viewQuery`" name several concrete capabilities with specific parameter-level detail, matching the 'several specific actions; minor gaps' anchor. Not 5 because coverage isn't comprehensive (e.g., no mention of asset types like Material/Prefab); not 3 because it goes beyond 1-2 generic actions.	4 / 5
Completeness	The 'what' is clear (read every serializable field and property of a Unity asset, with path-scoped reads), but there is no 'Use when...' clause or equivalent trigger guidance — "Use 'assets-find' to find the asset first" is a prerequisite instruction, not a when-to-use trigger. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms are present — "asset data", "Unity project", "serializable field and property", "asset" — giving good keyword coverage for the domain. Not 5 because common variations users would say (e.g., "inspect a prefab", "read a Material", "ScriptableObject") are missing.	4 / 5
Distinctiveness Conflict Risk	"Get asset data from the asset file in the Unity project" carves a clear niche that is distinct from the sibling 'assets-find' tool, matching 'mostly distinct; minor overlap risk'. Not 5 because it could still overlap with other Unity asset-inspection skills sharing the same trigger words.	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/assets-get-data/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.