screenshot-camera

Capture a screenshot from a Unity `Camera` and return it as a PNG image for direct LLM inspection. Falls back to `Camera.main` (then any active camera) when `cameraRef` is null. Width and height are capped to keep response size manageable.

Quality

73%

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/screenshot-camera/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.

A well-structured, self-contained API-style skill doc with executable commands and clear internal-behavior documentation. Its weaknesses are redundant parameter documentation (prose section + table + schema) and example invocation values that contradict the stated input constraints.

Suggestions

Deduplicate the parameter documentation: keep either the `## Inputs` prose section or the `## Input` table, not both.

Replace the placeholder example values ("width": 0, "height": 0) with realistic ones (e.g. 1920/1080) that satisfy the documented "> 0" constraint so the example is copy-paste ready.

Move the full Input JSON Schema into a `references/schema.md` (or trim it to the non-obvious `AIGD.GameObjectRef` fields) to slim the body and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The `## Inputs` prose section and the `## Input` table state the same three parameters twice, and the ~50-line inlined JSON schema largely duplicates that table. The writing itself is tight with no concept over-explanation, but the evident duplication means it "could be tightened" rather than being efficient — matching anchor 3, not 4.	3 / 5
Actionability	Provides real, executable `unity-mcp-cli run-tool screenshot-camera` commands in three invocation forms plus a concrete troubleshooting path (npm install -g / npx fallback). Minor gap: the example uses placeholder values ("width": 0, "height": 0) that violate the documented "> 0" constraint if copied literally, keeping it from fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	This is a simple single-action tool and the "How to Call" instruction is unambiguous; the `## Behavior` section sequences the internal steps (allocate RenderTexture, render, read back, encode, restore) and troubleshooting covers recovery for the main failure mode. The invalid placeholder example values are the minor gap that keeps it below 5.	4 / 5
Progressive Disclosure	Self-contained skill (no bundle files exist) with well-organized, consistently headed sections covering summary, inputs, behavior, invocation, and troubleshooting. The inlined JSON schema block is content that could live in a reference file and pushes the body past the ~50-line simple-skill sweet spot, so structure is good but not optimal.	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.

A specific, concrete description that clearly communicates what the tool does and how it behaves, with good natural trigger terms around Unity screenshots. Its main weakness is the complete absence of "when to use" guidance, which caps completeness and weakens triggerability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to see or visually inspect the current Unity scene/game view, or mentions screenshots or capturing what the camera sees."

Include natural synonyms such as "screen capture", "viewport", or "game view" to broaden keyword coverage toward the top anchor.

Clarify who consumes the output ("for direct LLM inspection" could name the returned image/caption) to round out coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Capture a screenshot from a Unity `Camera`", "return it as a PNG image for direct LLM inspection", explicit fallback behavior ("Falls back to `Camera.main` (then any active camera) when `cameraRef` is null"), and dimension capping. Minor gaps in coverage keep it below the comprehensive anchor 5, but it is well above the 1–2-action anchor 3.	4 / 5
Completeness	The "what" is clearly stated (capture screenshot, return PNG, fallback chain, size capping), but there is no "when" clause or equivalent trigger guidance anywhere. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	"screenshot", "capture", "Unity", "Camera", "PNG", and "image" give good natural keyword coverage — "screenshot" is exactly what a user would say. A few natural variants ("screen capture", "viewport", "game view") are missing, so it does not reach the synonym-comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	"Unity `Camera`" pins a distinct niche unlikely to trigger for non-Unity image or file skills. Minor overlap risk remains with other screenshot/capture-oriented tools, so it stops short of the clear-niche anchor 5.	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/screenshot-camera/SKILL.md
Commit: 4c8056f

Reviewed: 8 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.