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

67%

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

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 with genuinely executable CLI and code examples, but it carries significant duplication (parameter rules and the SerializedMember schema each appear twice) and offers no validation/verification guidance for checking execution results. A single complete end-to-end example would make it fully copy-paste ready.

Suggestions

Deduplicate: keep the Unity-object parameter rules in one place (the Input table) and reference it from the 'Passing Unity objects' section; define the SerializedMember schema once and have the Output section reference it instead of repeating it.

Add a short 'Verifying results' note: how to read the returned `result` field and what to do on a compile error (fix csharpCode and retry).

Replace the "string_value" placeholder call with one complete, runnable example that includes a parameters entry (e.g. disabling a GameObject by name) to cover the most common case end-to-end.

Dimension	Reasoning	Score
Conciseness	The body avoids concept explanations Claude already knows, but the Unity-object resolution rules are duplicated nearly verbatim between the 'Passing Unity objects' section and the `parameters` table row, and the ~45-line SerializedMember JSON schema is repeated in full in both Input and Output sections.	3 / 5
Actionability	Concrete copy-paste CLI invocations (including the --input-file heredoc pattern), executable C# examples, and explicit parameter value formats provide mostly executable guidance; the 'How to Call' block uses "string_value" placeholders rather than one complete end-to-end example with a parameter entry.	4 / 5
Workflow Clarity	Mode selection (full-code vs body-only) and the invocation are clearly specified, but there are no validation checkpoints — nothing on interpreting the returned `result`, handling compile errors, or confirming effects — fitting the anchor 'sequence present but checkpoints missing'.	3 / 5
Progressive Disclosure	Sections are well organized (Modes, Parameters, How to Call, Troubleshooting, Input, Output), but no bundle files exist and ~130 lines of inline JSON schemas are content that could be split into reference files; the pointer to the sibling unity-initial-setup skill has no reference structure around it.	3 / 5
	Total	13 / 20 Passed

Description

61%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 states concrete capabilities in a distinct niche with decent trigger keywords, but it lacks any 'when to use this' guidance, which caps completeness. A short trigger clause naming natural usage scenarios would raise it substantially.

Suggestions

Add a 'Use when...' clause, e.g. "Use when the user asks to run, test, or execute C# code in the Unity editor, compile C# snippets, or manipulate Unity objects from code."

Include a couple of natural trigger variations and synonyms ("run C#", "C# script", "Unity runtime") to broaden keyword coverage.

Compress the "see the skill body" pointer or replace it with a one-line summary of the mode difference so the description stands alone.

Dimension	Reasoning	Score
Specificity	"Compiles and executes C# code dynamically using Roslyn" names the domain with two concrete actions plus two modes, matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	The 'what' is clear (compiles/executes C# via Roslyn with two modes) but there is no 'Use when...' trigger clause; "see the skill body" is navigation, not usage guidance, so completeness is capped at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage ("C# code", "executes", "Unity object references") that users would plausibly say, though common variations like "run C# script" or ".cs" are missing.	4 / 5
Distinctiveness Conflict Risk	"Roslyn", "C#", and "Unity object references" form a distinct niche with minimal conflict risk, though it could still overlap with other code-execution skills.	4 / 5
	Total	14 / 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: 4c8056f

Reviewed: 9 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.