CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

screenshot-isolated

Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (solid/skybox/transparent), multi-light setup via JSON, and Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image. When isolated=true, inactive children may briefly fire OnEnable — see the body for side-effect notes.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Unity-MCP-Plugin/.claude/skills/screenshot-isolated/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A well-organized, domain-appropriate tool reference with genuinely useful details (camera views, background modes, lights config, side-effect caveats, troubleshooting). Its main weaknesses are redundancy — the parameter set is documented twice in different formats — and a placeholder-only invocation example instead of a realistic filled call.

Suggestions

Replace the all-'string_value' placeholder invocation with one realistic, copy-paste-ready example (e.g. gameObjectRef by path, isolated=true, cameraView='Composite', resolution=512) while keeping the brief stdin/input-file variants.

Move the full Input JSON Schema to a references/input-schema.json file and link to it, keeping the Input table as the in-body summary — this removes ~115 lines of duplication.

Clarify actual parameter types in the Input table (boolean/number/string instead of 'any') so users can construct correct JSON without consulting the schema.

DimensionReasoningScore

Conciseness

The body is reference-dense and free of concept over-explanation, but it duplicates itself: the Input table and the ~115-line Input JSON Schema describe the same parameters, and the 'How to Call' template lists all 12 parameters as literal 'string_value' placeholders plus three invocation variants. This matches 'mostly efficient but could be tightened' rather than level 4's 'minor instances of over-explanation'.

3 / 5

Actionability

Concrete, executable CLI commands are given in three working forms (inline, --input-file, stdin heredoc), and the Input table documents concrete defaults plus a realistic lights JSON example. Not 5 because the primary invocation is a placeholder template with 'string_value' for every parameter (misleading for boolean/numeric fields) rather than a copy-paste-ready filled example.

4 / 5

Workflow Clarity

For a single-call tool the action is unambiguous: pick parameters from a well-documented table, invoke one CLI command, receive a PNG. The side-effect caveat section appropriately warns when to set isolated=false. Not 5 because the placeholder template leaves it implicit how to fill each field (all shown as 'string_value'), leaving a minor gap between the documented inputs and a correct invocation; not 3 because there is no multi-step destructive or batch workflow requiring validation checkpoints.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all content is inline in a ~200-line body. Section headers are clear, but the full Input JSON Schema (~115 lines) is exactly the kind of bulk reference material that should live in a separate file, matching 'some structure but content that should be separate is inline' rather than level 4's 'most content appropriately placed'.

3 / 5

Total

14

/

20

Passed

Description

67%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.

A highly specific, jargon-appropriate description of the tool's capabilities, but it reads as a tool API summary rather than a skill description: it never says when to invoke it, and it omits the most natural trigger words ('screenshot', 'capture', 'Unity'). Adding a 'Use when...' clause would resolve the completeness cap.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a screenshot, render, or preview image of a Unity GameObject or prefab, or wants to capture an object in isolation.'

Include natural trigger synonyms and terms users actually say — 'screenshot', 'capture', 'preview', 'Unity' — rather than only implementation vocabulary like 'layer-based culling'.

Shorten the side-effect caveat ('inactive children may briefly fire OnEnable — see the body for side-effect notes') since it is detailed in the body; keep the description focused on what/when.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete capabilities — 'Render a target GameObject from a chosen camera angle', 'layer-based isolation', 'configurable background (solid/skybox/transparent)', 'multi-light setup via JSON', 'Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image.' — with comprehensive coverage and no filler. It is not the level below (4) because coverage is comprehensive rather than having minor gaps.

5 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent trigger guidance; the only 'When' phrasing ('When isolated=true, inactive children may briefly fire OnEnable') is a behavioral caveat, not usage guidance. Per the judging guideline, a missing 'Use when' clause caps completeness at 3 — clear 'what', missing 'when'.

3 / 5

Trigger Term Quality

Relevant Unity-domain terms are present ('GameObject', 'camera angle', 'skybox', 'PNG', 'render'), but the most natural user phrasings — 'screenshot', 'capture', 'image of an object', 'Unity' — are absent. This matches the anchor 'Some relevant keywords but missing common variations or synonyms' rather than level 4, whose keyword coverage would include the obvious natural trigger 'screenshot'.

3 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche — Unity GameObject rendering with layer-based isolation — with triggers ('GameObject', 'skybox', 'layer-based isolation', 'Composite') unlikely to fire for unrelated skills. Not 4 because there is no meaningful overlap risk with other skills; the vocabulary is domain-locked to Unity editor tooling.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

IvanMurzak/Unity-MCP

Path

Unity-MCP-Plugin/.claude/skills/screenshot-isolated/SKILL.md

Reviewed

Table of Contents

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.