canvas-design
Create original visual design philosophies and express them as meticulously crafted, museum-quality PNG or PDF art with minimal text — generative art, data visualization, and abstract compositions.
Best use case
canvas-design is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create original visual design philosophies and express them as meticulously crafted, museum-quality PNG or PDF art with minimal text — generative art, data visualization, and abstract compositions.
Teams using canvas-design should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/canvas-design/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How canvas-design Compares
| Feature / Agent | canvas-design | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Create original visual design philosophies and express them as meticulously crafted, museum-quality PNG or PDF art with minimal text — generative art, data visualization, and abstract compositions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Canvas Design Skill
## When to use
- Creating generative art and abstract compositions
- Designing visual assets with HTML Canvas or SVG
- Building data visualizations as art
- Creating unique brand assets and illustrations
## Canvas setup
```js
const canvas = document.createElement("canvas");
const ctx = canvas.getContext("2d");
const dpr = window.devicePixelRatio || 1;
canvas.width = 1200 * dpr;
canvas.height = 800 * dpr;
canvas.style.width = "1200px";
canvas.style.height = "800px";
ctx.scale(dpr, dpr);
```
## Composition patterns
### Grid-based generative
```js
const cols = 12, rows = 8;
const cellW = 1200 / cols, cellH = 800 / rows;
for (let x = 0; x < cols; x++) {
for (let y = 0; y < rows; y++) {
ctx.save();
ctx.translate(x * cellW + cellW / 2, y * cellH + cellH / 2);
ctx.rotate(Math.random() * Math.PI);
// Draw shape
ctx.fillStyle = `hsl(${200 + Math.random() * 60}, 70%, ${50 + Math.random() * 20}%)`;
ctx.fillRect(-cellW / 4, -cellH / 4, cellW / 2, cellH / 2);
ctx.restore();
}
}
```
### Noise-based organic
```js
// Use simplex/perlin noise for organic patterns
for (let x = 0; x < width; x += 2) {
for (let y = 0; y < height; y += 2) {
const n = noise(x * 0.005, y * 0.005);
const hue = 200 + n * 60;
ctx.fillStyle = `hsl(${hue}, 60%, ${40 + n * 30}%)`;
ctx.fillRect(x, y, 2, 2);
}
}
```
## Export
```js
// PNG
canvas.toBlob((blob) => {
const url = URL.createObjectURL(blob);
const a = document.createElement("a");
a.href = url; a.download = "artwork.png"; a.click();
}, "image/png");
// High-res: use 3x DPR for print-quality output
```
## Design philosophy
- **Constraint breeds creativity**: Limit colors (3-5), shapes, and rules
- **Randomness with structure**: Random parameters within defined bounds
- **Iteration**: Generate many, curate the best
- **Minimal text**: Let the visual speak
## Tips for AI Agents
- Ask about the desired mood, color palette, and output format.
- Generate multiple variations and let the user choose.
- Consider print resolution (300 DPI) for physical outputs.Related Skills
web-design-reviewer
Inspect web interfaces for layout, responsive, accessibility, and visual issues, then apply targeted source code fixes and re-verify results.
ui-design-system
Create and maintain scalable UI design systems with design tokens, responsive rules, accessibility standards, component libraries, and developer handoff documentation.
tailwind-design-system-v4
Build scalable, responsive, and accessible design systems with Tailwind CSS v4 — design tokens, theme configuration, reusable React UI components, and migration from v3.
responsive-design
Master modern responsive design techniques — container queries, fluid typography with clamp(), CSS Grid, Flexbox patterns, and mobile-first strategies for adaptive interfaces.
pricing-page-design
Design high-conversion SaaS pricing pages with plan structures, comparison patterns, conversion strategies, copy templates, SEO/AEO checklists, and layout types (3-card, slider, persona split, enterprise).
motion-canvas-animate
Create programmatic animations using Motion Canvas at {{MOTION_CANVAS_HOST}}:{{MOTION_CANVAS_PORT}}.
landing-page-design
Design high-conversion landing pages with structure, section order, layout types (classic hero, long-form, minimal, comparison), conversion strategies, SEO/AEO guidance, and copywriting templates.
interaction-design
Design and implement purposeful UI motion, microinteractions, and feedback patterns to enhance usability and user delight — hover effects, transitions, loading states, and gesture responses.
frontend-distinctive-design
Create distinctive, production-grade frontend interfaces with bold, cohesive aesthetics and refined implementation — visual identity, typography systems, color palettes, and layout composition.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
youtube-growth
Act as an expert YouTube Strategy Consultant. Apply the Creator Unlock N.I.C.E.R. Framework for conducting channel audits, niche validation, and data-backed video ideation/thumbnail generation.
xyops-automate
Build and manage automation pipelines using xyOps at {{XYOPS_HOST}}:{{XYOPS_PORT}}.