Image generation branding
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill image-generation-brandingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Guidelines for applying strict brand color palettes and minimalist technical design standards to generated imagery.
SKILL.md
0.8 KB, as published. Nobody here has run it
Branding Principles
- Minimalism: Avoid gradients, shadows, or high-saturation colors unless explicitly requested.
- Palette Control: Utilize strict hex-based mapping for corporate components.
- Visual Hierarchy: Clearly separate technical layers using consistent line weights (Muted Mid Gray).
- Typography: Use sans-serif, low-weight headers for technical documentation.
Implementation Checklist
- Identify all required components (e.g., Casing, PCB, Battery).
- Map components to requested color tokens.
- Ensure background matches the Brand Identity Light.
- Final Review: Compare against core brand tokens for saturation and style adherence.