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

71%

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

76%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 highly actionable with executable commands and a clean structure, and it avoids over-explaining known concepts, but it lacks validation/verification guidance for a destructive runtime-execution operation and carries some duplicated detail plus bulky inline schemas.

Suggestions

Add a validation step after the tool call, e.g. check the returned `result` for success/failure and log/branch on errors before proceeding, to lift workflow_clarity above 3.

De-duplicate the Unity object reference resolution detail: keep it once (in the table or the dedicated section) and cross-reference the other location.

Move the full input/output JSON schemas into a reference file (e.g. references/schemas.md) and link to it, keeping only the key fields inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining basic concepts Claude already knows, but the long `csharpCode` and `parameters` table cells duplicate the Unity-object-resolution detail already given in the "Passing Unity objects" section, leaving minor trim opportunities that keep it below a 5.	4 / 5
Actionability	Copy-paste-ready bash commands with a concrete JSON example, input-file and stdin variants, explicit mode examples, and a troubleshooting note fully cover the common call cases as the 5 anchor requires.	5 / 5
Workflow Clarity	Although the single tool call is unambiguous, executing arbitrary C# in a live Unity runtime is a destructive/risky operation and the body provides no validation or verification checkpoint for the returned result; the rubric caps such skills at 3.	3 / 5
Progressive Disclosure	Sections are clearly organized (Modes, Passing Unity objects, How to Call, Input, Output) with one clearly-signaled cross-skill reference, but the two bulky inline JSON schemas (input and output) could be externalized, a minor organization gap below the ideal 5.	4 / 5
	Total	16 / 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 clearly conveys what the skill does (dynamic C# compilation/execution via Roslyn with two modes) and is reasonably specific and distinct, but it omits any explicit "when to use it" trigger guidance, capping completeness at 3.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when the user asks to run C# code inside Unity, test a script snippet, or manipulate GameObjects/Components at runtime."

Include the .cs file extension and synonyms (e.g. "C# snippets", "Roslyn scripts") to broaden natural trigger-term coverage.

Briefly state what distinguishes body-only vs full-code mode in the description rather than deferring entirely to the body.

Dimension	Reasoning	Score
Specificity	Quotes "Compiles and executes C# code dynamically using Roslyn" name two concrete actions plus two modes (full-code/body-only); not quite the comprehensive multi-action list of a 5 but above the 1-2 actions of a 3.	4 / 5
Completeness	A clear "what" is stated (compiles and executes C# dynamically) but there is no "when"/"Use when..." trigger clause — only "see the skill body" — which the guideline caps at 3.	3 / 5
Trigger Term Quality	Natural terms like "C# code", "Roslyn", and "Unity object references" are present, but synonyms and file extensions (.cs) are missing, fitting the "good coverage, a few terms missing" anchor rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The Roslyn + Unity-object-reference niche is clearly distinct with minimal conflict risk; it is not the zero-overlap 5 because closely related Unity script-execution skills could overlap.	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/script-execute/SKILL.md
Commit: 07b8f65

Reviewed: 3 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.