Anthropic brand
Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/anthropic-poster-design/anthropic-brand
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill anthropic-brandAssembled 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
Anthropic's official brand color palette, typography, and design tokens for use in branded materials.
SKILL.md
1.4 KB, as published. Nobody here has run it
Anthropic Brand Design System
Color Palette (from anthropic.com)
| Token Name | Hex | Usage |
|---|---|---|
| Identity Light | #F5F4ED | Page/poster backgrounds, light fills |
| Corporate Dark | #141413 | Primary text, dark surfaces, casing |
| Primary Brand Accent | #D97757 | Interactive highlights, connectors |
| Secondary Brand Accent | #EDA100 | Supporting accent, warm highlights |
| Tertiary Brand Accent | #A18A74 | Substrate fills, muted elements |
| Muted Mid Gray | #B0ADA5 | Annotation lines, secondary text |
Typography
- Heading/Display: Anthropic uses a clean serif via
var(--serif)CSS variable on their site. The publicly served font resolves to a refined serif face. When unavailable, use a clean sans-serif like DejaVu Sans as fallback. - Body/UI: Clean sans-serif via
var(--sans). - Monospace: For code/technical labels.
Design Principles
- Minimalist: Low saturation, warm tones, generous whitespace
- No neon/gradients: Avoid high-intensity AI-style gradients
- Warm palette: Cream backgrounds, earthy accents, muted neutrals
- Clean geometry: Simple shapes, thin annotation lines