CtrlK
BlogDocsLog inGet started
Tessl Logo

assets-find

Search the Unity asset database using a search filter string. The filter accepts names, labels (`l:`), types (`t:`), AssetBundles (`b:`), areas (`a:`), and globs (`glob:`). See the body for the full filter syntax.

60

Quality

75%

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-find/SKILL.md
SKILL.md
Quality
Evals
Security

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 is a well-structured, actionable single-purpose tool reference with executable call syntax and troubleshooting. Its main weaknesses are verbatim duplication of the filter syntax inside the input table and the absence of a worked example with a real filter value.

Suggestions

Replace the placeholder example with a realistic one, e.g. unity-mcp-cli run-tool assets-find --input '{"filter": "t:Prefab l:player", "maxResults": 50}', plus a short sample of the returned asset references.

Deduplicate the `filter` row in the Input table — reference the Filter syntax section instead of restating it verbatim.

Trim the inline output JSON schema to a compact example output (instanceID, assetPath, assetGuid, assetType) and drop the redundant $defs boilerplate.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the `filter` row in the Input table restates the entire Filter syntax section nearly verbatim, and the input table plus full JSON schema duplicate each other's information. Not a 2 because there is no padding or explanation of concepts Claude already knows; not a 4 because the duplication is substantial and easily trimmed.

3 / 5

Actionability

The CLI invocation is concrete and executable ("unity-mcp-cli run-tool assets-find --input '...'") with a complete JSON template, plus troubleshooting for a missing CLI. Not a 5 because the example uses only "string_value" placeholders — there is no copy-paste-ready example with a realistic filter such as "t:Prefab l:player".

4 / 5

Workflow Clarity

As a simple single-task skill, the one action is unambiguous: filter syntax, call command, troubleshooting, and output schema are all laid out in a clear order. Not a 5 because the placeholder-only call example leaves minor ambiguity about composing multi-token filters and interpreting truncated results.

4 / 5

Progressive Disclosure

Sections are well organized (Filter syntax, How to Call, Troubleshooting, Input, Output) with no nested or buried references, and nothing requires external files. Not a 5 because the ~50-line output JSON schema and the duplicated filter documentation are bulky inline content that a leaner inline summary could replace.

4 / 5

Total

15

/

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 specific, well-scoped description with strong domain keywords and low conflict risk, but it omits any "Use when..." trigger guidance, which limits its discoverability. Adding an explicit trigger clause and a few natural synonyms (e.g., "find/locate assets") would raise it substantially.

Suggestions

Add a 'Use when...' clause, e.g. "Use when searching for Unity assets such as prefabs, textures, or materials, or when the user mentions asset labels, asset types, or AssetBundles."

Include natural synonyms users would say — "find", "locate", "prefab", "texture", "scriptable object" — alongside the technical filter markers.

Optionally mention the connection to downstream workflows (e.g., using returned asset paths/GUIDs with other tools) to sharpen the when-to-use signal.

DimensionReasoningScore

Specificity

"Search the Unity asset database using a search filter string" plus the enumerated filter capabilities (names, labels `l:`, types `t:`, AssetBundles `b:`, areas `a:`, globs `glob:`) list several concrete capabilities with only minor gaps. Not a 5 because it describes a single search action with parameter detail rather than multiple distinct concrete actions.

4 / 5

Completeness

The "what" is clear (search the Unity asset database with a filter string), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the "what" is concrete and detailed, not vague.

3 / 5

Trigger Term Quality

Good keyword coverage with natural domain terms: "Unity asset database", "search", "labels", "types", "globs". A few natural user phrasings are missing, such as "find assets", "locate prefabs", or asset-type synonyms users would actually say.

4 / 5

Distinctiveness Conflict Risk

It is firmly anchored to the Unity asset database with distinctive filter syntax markers (`l:`, `t:`, `b:`, `a:`, `glob:`), giving it a clear niche with minimal conflict risk against generic search or file skills.

5 / 5

Total

16

/

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.

Validation — 16 / 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.