threejs-image-generator

Generate and edit 2D image assets for Three.js games with Google's Gemini image API: concept sheets, image-to-3D inputs, texture and material references, sky and background plates, decals, logos, icons, GUI art, title and menu art, and marketing stills. Also use for direct image editing when the user supplies an image path.

Quality

83%

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

Quality

Content

82%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 tight, highly actionable skill body with concrete commands, prompt templates, and clear integration/recovery guidance, appropriately split into a single script bundle. It would benefit from an explicit numbered validation feedback loop for paid generations and trimming a few verbose passages.

Suggestions

Add an explicit numbered validate→fix→retry feedback loop for paid generations (e.g. probe → generate → inspect result before dependent variants → on transient error, preserve and reconcile rather than retry).

Tighten the directory-resolution paragraph and reduce overlap between 'When to use' and the frontmatter description to recover tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no over-explanation of Three.js or image concepts — but the directory-resolution paragraph and some overlap between 'When to use' and the description leave minor trim opportunities.	4 / 5
Actionability	Provides copy-paste-ready commands ('uv run <this-skill-dir>/scripts/generate_image.py ... --prompt ... --filename ... --resolution 2K'), a credential probe, an image-to-3D editing example with --input-image, and ready-to-use prompt-pattern templates covering the common cases.	5 / 5
Workflow Clarity	A clear implicit sequence (probe key → generate → inspect → integrate → report) with a credential validation checkpoint and recovery guidance is present, but there is no explicit numbered validate→fix→retry feedback loop for the paid-generation path.	4 / 5
Progressive Disclosure	Well-organized sections keep the overview in SKILL.md while the implementation lives in the real, referenced scripts/generate_image.py bundle file, and sibling-skill references are one-level and signaled; the external director reference paths (asset-recovery.md, probe script) are not part of this skill's bundle, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

83%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, well-scoped description that names a comprehensive set of concrete 2D asset actions and an explicit editing trigger, anchored to a distinct Three.js + Gemini niche. The main generation trigger is implied rather than stated as an explicit 'Use when' phrase, leaving the 'when' slightly narrow.

Suggestions

Add an explicit 'Use when generating 2D image assets for Three.js games' trigger phrase so the primary generation case has direct trigger guidance, not just the editing sub-case.

Include a few natural synonyms or file extensions (e.g. concept art, sprites, .png) to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across a comprehensive set of asset types — 'concept sheets, image-to-3D inputs, texture and material references, sky and background plates, decals, logos, icons, GUI art, title and menu art, and marketing stills' plus 'direct image editing when the user supplies an image path'.	5 / 5
Completeness	A clear, comprehensive 'what' is present and an explicit 'when' clause exists for editing ('when the user supplies an image path'), but the primary generation use case relies on implied triggers rather than an explicit 'Use when generating...' phrase, so 'when' could be more explicit.	4 / 5
Trigger Term Quality	Strong natural terms users would say ('textures', 'decals', 'logos', 'icons', 'GUI art', 'sky and background plates', 'image editing'), but missing common synonyms and file extensions (e.g. .png, sprites, concept art) that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	The 'Three.js games' + 'Gemini image API' framing with specific 2D asset categories carves a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 8 missing, 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: majidmanzarpour/threejs-game-skills
Path: skills/threejs-image-generator/SKILL.md
Commit: e5f301d

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.