algorithmic-art
Skill4 starsChanged 7 months agoMITView on GitHub
Create algorithmic generative art using p5.js with seeded randomness and interactive parameter exploration. Use when users request generative art, algorithmic art, creative coding, flow fields, particle systems, or computational art. Outputs an interactive HTML artifact with parameter controls. Keywords: generative art, p5.js, algorithmic, flow field, particle system, creative coding, computational art, procedural art.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 164 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Create algorithmic generative art using p5.js — self-contained interactive HTML artifacts with parameter controls and seed navigation.
- Distinctive: line 16
Every piece follows this creative pipeline:
- Distinctive: line 34
Before coding, write a 4-6 paragraph philosophy:
- Very specific: line 193
Performance: Use noLoop() for static art.
“Common” is measured: kept by at least 6 in 10 of the 164 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Algorithmic Art
Create algorithmic generative art using p5.js — self-contained interactive HTML artifacts with parameter controls and seed navigation.
Process
Every piece follows this creative pipeline:
- Interpret the user's intent — what aesthetic, mood, or concept?
- Create an Algorithmic Philosophy — a 4-6 paragraph computational worldview describing the generative approach
- Implement in p5.js — build the algorithm expressing the philosophy
- Design parameters — what should be tunable? (quantities, scales, speeds, thresholds)
- Build UI controls — sliders and inputs for all parameters
Output Format
One self-contained HTML file containing:
- p5.js loaded from CDN
- The generative algorithm (setup/draw/classes)
- Sidebar with: Seed navigation + Parameter controls + Action buttons
- Everything works immediately in any browser or claude.ai artifacts
Algorithmic Philosophy Creation
Before coding, write a 4-6 paragraph philosophy:
# [Movement Name] — e.g., "Organic Turbulence"
[Paragraph 1: Core philosophical idea — what computational truth does this art reveal?]
[Paragraph 2: How does randomness and order interact in this system?]
[Paragraph 3: What forces, behaviors, or mathematical relationships drive the visual?]
[Paragraph 4: How does time/animation express the underlying process?]
[Paragraph 5: Why does this algorithm feel inevitable and meticulously crafted?]HTML Artifact Structure
<!DOCTYPE html>
<html>
<head>
<script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js"></script>
<style>
body { display: flex; margin: 0; font-family: Arial, sans-serif; background: #faf9f5; }
#canvas-container { flex: 1; }
#sidebar { width: 280px; padding: 20px; background: #fff; border-left: 1px solid #e8e6dc; overflow-y: auto; }
.control-group { margin-bottom: 16px; }
label { display: block; font-size: 12px; color: #141413; margin-bottom: 4px; }
input[type=range] { width: 100%; }
.value-display { font-size: 11px; color: #b0aea5; }
button { width: 100%; padding: 8px; margin-bottom: 8px; background: #d97757; color: white; border: none; border-radius: 4px; cursor: pointer; }
button:hover { background: #c4674a; }
h3 { font-size: 13px; color: #141413; border-bottom: 1px solid #e8e6dc; padding-bottom: 8px; }
</style>
</head>
<body>
<div id="canvas-container"></div>
<div id="sidebar">
<h3>Seed</h3>
<div class="control-group">
<span id="seed-display">Seed: 1</span><br>
<button onclick="prevSeed()">← Prev</button>
<button onclick="nextSeed()">Next →</button>
<button onclick="randomSeed_()">Random</button>
</div>
<h3>Parameters</h3>
<!-- VARIABLE: Add parameter controls here -->
<div class="control-group">
<label>Particle Count</label>
<input type="range" id="count" min="100" max="2000" step="100" value="500"
oninput="params.count=+this.value; document.getElementById('count-val').textContent=this.value; regenerate()">
<span class="value-display" id="count-val">500</span>
</div>
<h3>Actions</h3>
<button onclick="regenerate()">Regenerate</button>
<button onclick="resetParams()">Reset</button>
<button onclick="saveCanvas('art', 'png')">Download PNG</button>
</div>
<script>
let seed = 1;
let params = { count: 500, speed: 1.0, noiseScale: 0.003 };
function prevSeed() { seed = Math.max(1, seed-1); document.getElementById('seed-display').textContent='Seed: '+seed; regenerate(); }
function nextSeed() { seed++; document.getElementById('seed-display').textContent='Seed: '+seed; regenerate(); }
function randomSeed_() { seed=Math.floor(Math.random()*10000); document.getElementById('seed-display').textContent='Seed: '+seed; regenerate(); }
function regenerate() { redraw(); }
function resetParams() { /* reset sliders to defaults */ }
// YOUR p5.js ALGORITHM BELOW
function setup() {
let canvas = createCanvas(800, 800);
canvas.parent('canvas-container');
randomSeed(seed);
noiseSeed(seed);
background(10, 10, 40);
noLoop(); // or loop() for animated
}
function draw() {
randomSeed(seed);
noiseSeed(seed);
// YOUR GENERATIVE ALGORITHM HERE
}
</script>
</body>
</html>Animation Primitives
Flow Field (Perlin Noise)
// Particle following noise-driven vector field
class Particle {
constructor() {
this.pos = createVector(random(width), random(height));
this.vel = createVector(0, 0);
this.acc = createVector(0, 0);
this.life = 255;
}
update() {
let angle = noise(this.pos.x * params.noiseScale, this.pos.y * params.noiseScale) * TWO_PI * 4;
this.acc = p5.Vector.fromAngle(angle).mult(params.speed);
this.vel.add(this.acc).limit(3);
this.pos.add(this.vel);
this.life -= 2;
}
draw() {
stroke(255, 200, 100, this.life);
point(this.pos.x, this.pos.y);
}
isDead() { return this.life <= 0 || this.pos.x < 0 || this.pos.x > width || this.pos.y < 0 || this.pos.y > height; }
}Recursive Branching (L-Systems)
function branch(x, y, angle, len, depth) {
if (depth === 0 || len < 2) return;
let x2 = x + cos(angle) * len;
let y2 = y + sin(angle) * len;
strokeWeight(depth * 0.5);
line(x, y, x2, y2);
let spread = random(0.3, 0.7);
branch(x2, y2, angle - spread, len * 0.72, depth - 1);
branch(x2, y2, angle + spread, len * 0.72, depth - 1);
}Voronoi / Stippling
// Weighted random point placement creating organic texture
let points = Array.from({length: params.count}, () => ({
x: randomGaussian(width/2, width/4),
y: randomGaussian(height/2, height/4)
}));
points.forEach(p => {
let sz = random(1, 4);
fill(255, random(100,200));
ellipse(p.x, p.y, sz, sz);
});Philosophy Examples
"Organic Turbulence": Chaos constrained by natural law. Flow fields driven by layered Perlin noise. Thousands of particles following vector forces, accumulating into organic density maps. Color emerges from velocity and density.
"Quantum Harmonics": Discrete entities exhibiting wave-like interference. Particles initialized on a grid, phases interfering — constructive interference creates bright nodes, destructive creates voids.
"Recursive Whispers": Self-similarity across scales. Branching structures subdividing recursively, constrained by golden ratios. Each branch slightly randomized, line weights diminishing with recursion.
Best Practices
- Always seed randomness:
randomSeed(seed)andnoiseSeed(seed)— same seed must produce identical output - Composable parameters: Extract magic numbers into
paramsobject with descriptive names - Performance: Use
noLoop()for static art; useframeRate(30)for smooth animation - Color harmony: Build palettes deliberately — 3-5 colors maximum for visual coherence
- The algorithm flows from the philosophy — don't pick a pattern menu, express the idea
Example
Input: "Create algorithmic art inspired by ocean waves"
Output:
- Philosophy: "Coastal Resonance" — oscillating systems where periodic motion creates apparent randomness. Sine waves at different frequencies interfere, creating moiré-like patterns that recall both mathematical certainty and oceanic unpredictability.
- Implementation: Layered sine wave lines moving across the canvas, each at slightly different frequency and amplitude. Color shifts from deep navy to seafoam based on wave height. Seed controls the frequency ratios, producing unique interference patterns.
- Interactive HTML artifact with controls for: wave count, frequency spread, color palette, animation speed.
Other versions169 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- nabcht/Zephyr★ 221% same
Wrote their own version · 168
- anthropics/skills★ 186ksame name
- Prat011/awesome-llm-skills★ 1.7ksame name
- google/adk-js★ 1.5ksame name
- ChenglinPoly/infiAgent★ 1.2ksame name
- polyuiislab/infiAgent★ 1.2ksame name
- syahiidkamil/Software-Engineer-AI-Agent-Atlas★ 393same name
- JetBrains/skills★ 386same name
- zephyrwang6/myskill★ 339same name
- xuzeyu91/WebCode★ 278same name
- maslennikov-ig/claude-code-orchestrator-kit★ 248same name
158 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use fal-generate, academy-guide and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
xfstudioSkillfal-generate
Generate images and videos using fal.ai AI models
Also in 5 projects that use this
AnthropicSkillacademy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
Also in 6 projects that use this
zephyrwang6Skilldeepl
Übersetzt Texte, Dokumente und XLIFF-Dateien via DeepL API. Verwende für Übersetzungen mit /deepl translate, /deepl file oder /deepl xliff.
Also in 4 projects that use this
zephyrwang6Skillimagemagick-conversion
Convert and manipulate images with ImageMagick. Covers format conversion, resizing, batch processing, quality adjustment, and image transformations. Use when user mentions image conversion, resizing images, ImageMagick, magick command, batch image processing, or thumbnail generation.
Also in 4 projects that use this
allanninalSkilllibafl
LibAFL is a modular fuzzing library for building custom fuzzers. Use for advanced fuzzing needs, custom mutators, or non-standard fuzzing targets.
Also in 4 projects that use this
jpoindexterSkillfal-restore
Restore and fix image quality — deblur, denoise, fix faces, and restore old documents using fal.ai's hosted restoration models.
Also in 3 projects that use this
- +4 more from zephyrwang6
In this repository112 other files it gives its agents.
- agentic-evalSkill
- agent-memorySkill
- agent-reachSkill
- agent-team-orchestrationSkill
- claude-apiSkill
- context-engineering-collectionSkill
- developer-growth-analysisSkill
- eval-harnessSkill
- exa-searchSkill
- langsmith-fetchSkill
- mcp-builderSkill
- prompt-engineering-patternsSkill
- rag-implementationSkill
- skill-creatorSkill
- subagent-driven-developmentSkill
- api-design-principlesSkill
- architecture-patternsSkill
- artifacts-builderSkill
- backend-patternsSkill
- changelog-generatorSkill
- clean-content-fetchSkill
- code-reviewSkill
- coding-standardsSkill
- computer-useSkill
- debug-proSkill
- docker-essentialsSkill
- e2e-testingSkill
- frontend-designSkill
- frontend-patternsSkill
- git-essentialsSkill
- microservices-patternsSkill
- modern-javascript-patternsSkill
- nextjs-app-router-patternsSkill
- postgresql-table-designSkill
- python-design-patternsSkill
- python-performance-optimizationSkill
- python-testing-patternsSkill
- react-state-managementSkill
- security-auditorSkill
- sql-toolkitSkill
- tdd-workflowSkill
- typescript-advanced-typesSkill
- using-git-worktreesSkill
- vue-best-practicesSkill
- webapp-testingSkill
- brand-guidelinesSkill
- canvas-designSkill
- comic-creatorSkill
- cover-imageSkill
- doc-coauthoringSkill
- docxSkill
- fal-ai-mediaSkill
- frontend-slidesSkill
- image-genSkill
- markdown-to-htmlSkill
- pdfSkill
- pptxSkill
- slide-deckSkill
- slidevSkill
- theme-factorySkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

