script-execute

Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/script-execute/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable CLI examples and clear parameter guidance, but it is held back by redundant inline JSON schemas and a lack of verification guidance for an operation that can change Unity state.

Suggestions

De-duplicate the JSON schemas: define the SerializedMember `$defs` once (or move schemas to a reference file) instead of repeating the block in both Input and Output.

Tighten the `csharpCode` table cell by splitting the run-on into short mode-specific notes instead of one long sentence.

Add a brief verification step (e.g. inspect the returned `result` or confirm the targeted GameObject changed) since executed C# can alter Unity state.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational reference material, but the full `$defs` SerializedMember block is duplicated verbatim across the input and output JSON schemas and the `csharpCode` table cell is a dense run-on, so it could be tightened.	2 / 3
Actionability	It provides copy-paste-ready, executable CLI invocations (`unity-mcp-cli run-tool script-execute --input …`, `--input-file`, stdin pipe) plus concrete parameter type examples, matching the 'fully executable commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The single tool invocation is unambiguous, but executing arbitrary C# can mutate Unity state and there is no verification/check step, so per the destructive-operations guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Sections are organized, but no bundle files exist and the large inline (and duplicated) JSON schemas are content that could be split into a reference file, fitting the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 distinct, clearly conveying what the skill does across its two modes. Its main weakness is the absence of explicit 'when to use' trigger guidance and slightly jargon-heavy (Roslyn) trigger terms.

Suggestions

Add a 'Use when…' clause naming natural triggers, e.g. 'Use when the user asks to run or execute C# code in Unity, prototype snippets, or manipulate Unity objects from C#'.

Soften jargon by pairing 'Roslyn' with a user-facing term like 'run C# scripts' so non-expert phrasing also matches.

Include common keyword variations ('C# script', 'run C#', 'Unity C#') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Compiles and executes C# code dynamically using Roslyn') and distinguishes two operating modes plus Unity object-reference passing, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers what the skill does but provides no 'Use when…' clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes relevant natural terms ('C# code', 'executes', 'Unity object references') but leans on the technical jargon 'Roslyn' and omits common variations like 'run C#' or 'C# script', fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche — dynamically compiling/executing C# via Roslyn within a Unity tooling context — is distinct and unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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/script-execute/SKILL.md
Commit: e0a24ef

Reviewed: about 11 hours 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.