object-get-data

Get serialized data for a Unity `UnityEngine.Object` — all serializable fields and properties. Supports token-saving path-scoped reads via `paths` or `viewQuery`. Pair with 'object-modify' when you need to write back.

Quality

72%

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/object-get-data/SKILL.md

Quality

Content

77%

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 concrete executable commands and well-organized sections for a simple read tool, but it embeds verbose JSON schemas inline rather than offloading them to reference files, hurting token efficiency and progressive disclosure.

Suggestions

Move the full Input and Output JSON schemas into reference files (e.g. references/input-schema.md, references/output-schema.md) and keep only the essential field table inline.

Consider extracting the ViewQuery field descriptions into a short reference, since they repeat detail already conveyed by the input table.

Retain the concise How-to-Call examples and troubleshooting block as the skill's core.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with no padding of concepts Claude already knows, but it embeds full input and output JSON schemas inline, which is token-heavy and could be tightened or moved out — matching the 'mostly efficient but could be tightened' anchor rather than 'every token earns its place'.	2 / 3
Actionability	It provides copy-paste-ready executable CLI commands (run-tool, --input-file, stdin pipe), documented path syntax, and fully specified input/output schemas with per-field descriptions, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	This is a simple single-action read tool with an unambiguous 'How to Call' section and a troubleshooting fallback; per the simple-skills scoring note, a single unambiguous action scores 3, and no destructive/batch operation requires validation checkpoints.	3 / 3
Progressive Disclosure	Sections are clearly organized (path-scoped reads, path syntax, how to call, input, output), but the skill exceeds 50 lines and keeps large JSON schemas inline rather than splitting them into reference files, matching the 'content that should be separate is inline' anchor; no bundle files are present.	2 / 3
	Total	10 / 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 clearly distinguishes the skill from its write counterpart, but it omits an explicit 'Use when...' trigger for the read scenario and its keywords are somewhat technical rather than naturally phrased.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you need to inspect or serialize a Unity object's fields and properties without modifying it.'

Broaden trigger terms with natural phrasings users would say, such as 'inspect Unity object', 'read object data', 'dump object fields'.

Keep the existing 'Pair with object-modify' boundary since it aids distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Get serialized data', 'all serializable fields and properties', 'path-scoped reads via paths or viewQuery', and pairing with object-modify — which matches the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers WHAT the skill does but lacks an explicit 'Use when...' trigger for the read case; the only 'when' is the write-back pairing, so per the missing-trigger-guidance rule completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms ('Unity', 'UnityEngine.Object', 'serialized data', 'fields and properties') but these lean technical and miss common natural variations a user might say, landing at the 'some relevant keywords but missing common variations' anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The Unity-object data-reading niche is distinct, and the 'Pair with object-modify' boundary explicitly separates it from the write skill, matching the 'clear niche with distinct triggers; unlikely to conflict' 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/object-get-data/SKILL.md
Commit: e0a24ef

Reviewed: about 12 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.