assets-shader-get-data

Get detailed data about a shader asset — properties, subshaders, passes, compilation messages, and supported status. Supports token-saving path-scoped reads via `paths` or `viewQuery`. Use 'assets-find' with `t:Shader` or 'assets-shader-list-all' to locate the shader first.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/assets-shader-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.

Highly actionable with concrete CLI examples and clear single-step usage, but token efficiency and progressive disclosure suffer from two large inline JSON schemas that should be externalized into reference files with links from the overview.

Suggestions

Move the Input and Output JSON schemas into separate reference files (e.g. references/input-schema.json, references/output-schema.json) and link to them from SKILL.md, keeping only a concise field overview inline.

Replace the all-`"string_value"` placeholder call with one realistic minimal example showing correct boolean/array types so it is immediately runnable.

De-duplicate the shared $defs (e.g. AIGD.AssetObjectRef and System.Type appear in both schemas) by referencing a shared types file to cut repeated tokens.

Dimension	Reasoning	Score
Conciseness	The prose sections are lean, but two full inline JSON schemas (~370 lines of repetitive $defs) are bulk that could be tightened or externalized; it avoids concept-explaining fluff (no score-1 'explains what a PDF is') yet does not reach the 'every token earns its place' level.	2 / 3
Actionability	Provides copy-paste-ready executable commands (`unity-mcp-cli run-tool ... --input '{...}'`, `--input-file`, stdin pipe), concrete path syntax, and a troubleshooting fallback (install globally / `npx`), matching the 'fully executable commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	This is a single read-only tool call with an unambiguous action and a stated prerequisite ('locate the shader first'); the simple-skills scoring note allows 3 for a single unambiguous action, and no destructive/batch validation gap applies.	3 / 3
Progressive Disclosure	Sections are clearly labeled (better than a monolithic wall, so not 1), but the large input/output JSON schemas are inline rather than split into separate reference files and no one-level-deep references are signaled, so it does not reach the 'content appropriately split; well-signaled references' level 3.	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with strong trigger terms and low conflict risk, weakened only by the absence of an explicit 'Use when...' trigger clause — the 'when' is conveyed as a prerequisite rather than a usage condition.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user needs detailed shader information (properties, passes, or compilation errors) for a specific shader asset.'

Frame the 'when' as a usage condition rather than only a prerequisite ('locate the shader first'), so Claude knows the situations that should prompt invoking this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete data categories — 'properties, subshaders, passes, compilation messages, and supported status' plus 'token-saving path-scoped reads via `paths` or `viewQuery`' — matching the 'lists multiple specific concrete actions' anchor rather than the 'names domain and some actions' level below.	3 / 3
Completeness	The 'what' is explicit, but the 'when' is only a prerequisite ('Use `assets-find` ... to locate the shader first') with no explicit 'Use when...' trigger clause, so per the rubric guidance completeness is capped at 2 rather than reaching the explicit-trigger level 3.	2 / 3
Trigger Term Quality	Natural shader-domain terms a Unity developer would say ('shader asset', 'properties', 'passes', 'compilation messages', `t:Shader`) give good coverage; it is well above the 'Works with PDF files' / 'some keywords but missing variations' level.	3 / 3
Distinctiveness Conflict Risk	The shader-asset niche plus named sibling tools ('assets-find', 'assets-shader-list-all') form a clear, distinct trigger unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 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/assets-shader-get-data/SKILL.md
Commit: e0a24ef

Reviewed: about 13 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.