script-read

Read a `.cs` script file and return its content as a string. Supports a 1-based `lineFrom`/`lineTo` slice for partial reads. Pair with 'script-update-or-create' to write back.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

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 content is actionable and well-structured with real executable commands and schemas, but it is held back by redundant triple-listing of inputs and a 'How to Call' example whose placeholder values contradict the documented defaults.

Suggestions

Consolidate the input specification into one place (e.g. keep the table and schema, drop the duplicated prose 'Inputs' section) to remove redundancy.

Fix the 'How to Call' example to use realistic values (e.g. "lineFrom": 1, "lineTo": -1) that match the documented defaults instead of 0/0.

Specify the clamping rules precisely (e.g. what happens when lineFrom > lineTo or lineFrom exceeds file length) to remove the remaining workflow ambiguity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the inputs are described three times (prose 'Inputs', the 'Input' table, and the 'Input JSON Schema'), which is redundant padding that could be tightened — fitting 'mostly efficient with some unnecessary content' better than a 4.	3 / 5
Actionability	Provides concrete, executable bash commands including stdin and --input-file variants plus full input/output JSON schemas, but the 'How to Call' example uses "lineFrom": 0, "lineTo": 0, which contradicts the documented defaults (1 and -1) and is a misleading minor gap, placing it just below copy-paste-perfect 5.	4 / 5
Workflow Clarity	This is a simple single-purpose read skill with an unambiguous action, explicit error behavior ('Throws if missing on disk'), clamping semantics, and a troubleshooting section; it is not a 5 because the exact clamping rules and the contradictory example values leave minor ambiguity.	4 / 5
Progressive Disclosure	Well-organized with clear section headers and a clearly-signaled one-level reference to the /unity-initial-setup skill; no nested references and no bundle files to misplace, though the inlined JSON schemas and triple-stated inputs represent minor organization gaps versus an ideal 5.	4 / 5
	Total	15 / 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 reasonably well-keyworded with a clear niche, but it omits any explicit 'Use when...' trigger guidance, which caps its completeness and limits overall quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to read, view, or inspect a C# script file, or needs a specific line range from a .cs file.'

Include common synonyms such as 'view' or 'show' alongside 'read' to broaden natural trigger coverage.

Clarify the relationship to 'script-update-or-create' with a one-word cue (e.g. 'read counterpart to') to sharpen distinctiveness from generic read tools.

Dimension	Reasoning	Score
Specificity	Names the domain (`.cs` script files) and several concrete actions — "return its content as a string", "1-based lineFrom/lineTo slice for partial reads", "Pair with 'script-update-or-create'" — with only minor coverage gaps, fitting the 'lists several specific actions' anchor better than the 1-2 actions of a 3.	4 / 5
Completeness	The 'what' is clear ("Read a `.cs` script file and return its content as a string"), but there is no 'Use when...' or equivalent trigger guidance, so per the rubric a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage including "read", "`.cs` script file", "content", and the file extension `.cs`, but missing common synonyms like "view" or "show" that users might say, so it is above a 3 but short of comprehensive 5-level coverage.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (`.cs` scripts with 1-based slicing and an explicit companion 'script-update-or-create'), leaving only minor overlap risk with generic file-read skills; not a 5 because the action 'read a file' is broadly shareable with other read skills.	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-read/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.