Generate high-quality images via MCP (Gemini models or compatible services) using structured prompts, ratios, and validation for marketing, UI, or presentations.
69
53%
Does it follow best practices?
Impact
97%
1.61xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/image-generation/SKILL.mdStructured prompt format & model selection
Subject field present
33%
100%
Style field present
100%
100%
Lighting field present
83%
100%
Mood field present
33%
100%
Composition field present
50%
100%
Aspect ratio per channel
100%
100%
Brand colors as HEX
100%
100%
Model selection with rationale
25%
100%
High-quality model for hero
0%
100%
Multiple variants planned
100%
100%
Metadata JSON structure
25%
66%
Style anchors consistent
90%
90%
Generation script & single-variable iteration
ask-gemini command used
0%
100%
Single variable per variant
100%
100%
3+ variants produced
100%
100%
Aspect ratio specified
100%
100%
Brand colors as HEX
100%
100%
Fast iteration model
0%
100%
Metadata saved per generation
100%
100%
Metadata JSON fields
100%
100%
Style anchor in base prompt
100%
100%
Structured prompt fields
100%
100%
Output report format & deliverables
Report heading
33%
100%
Request section
0%
83%
Request fields
50%
100%
Output Files section
12%
87%
Metadata section
0%
83%
Metadata fields
0%
100%
Usage Notes section
33%
83%
JSON metadata structure
80%
100%
Review: Brand fit
75%
100%
Review: Ratio correctness
100%
100%
Review: Composition clarity
25%
100%
Review: Text readability
12%
100%
Deliverables complete
100%
100%
fd18296
Table of Contents
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.