agentleFS
Sign inStart free
LucasCooperBeyLucasCooperBey/claude-skills/skills/algorithmic-art/SKILL.md

algorithmic-art

Skill1 starsChanged 5 months agoMITView on GitHub

Creates generative and computational art using p5.js with seeded randomness, particle systems, and interactive exploration. Covers creative coding and procedural aesthetics.

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 161 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create computational art using p5.js with seeded randomness and interactive exploration.

    line 7
  2. Distinctive:

    Create a manifesto describing the computational aesthetic (4-6 paragraphs):

    line 12

“Common” is measured: kept by at least 6 in 10 of the 161 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Algorithmic Art Creation

Create computational art using p5.js with seeded randomness and interactive exploration.

Core Process

Phase 1: Algorithmic Philosophy

Create a manifesto describing the computational aesthetic (4-6 paragraphs):

  • Emphasize emergent behavior
  • Focus on mathematical beauty
  • Express craftsmanship philosophy

Phase 2: P5.js Implementation

Express the philosophy through a single self-contained HTML artifact.

Key Principles

On Craftsmanship: The algorithm must feel meticulously crafted, refined through countless iterations by someone at the absolute top of their field.

On Generative Art: Focus on process over product. Each seed run produces unique outputs. Beauty emerges from algorithmic execution, not static composition.

Technical Requirements

Seeded Randomness (Art Blocks Pattern)

let seed;

function setup() {
  createCanvas(800, 800);
  seed = parseInt(getURLParams().seed) || floor(random(999999));
  randomSeed(seed);
  noiseSeed(seed);
}

Self-Contained HTML Structure

<!DOCTYPE html>
<html>
<head>
  <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.9.0/p5.min.js"></script>
  <style>
    body { margin: 0; display: flex; justify-content: center; align-items: center; min-height: 100vh; background: #111; }
    canvas { display: block; }
    .controls { position: fixed; bottom: 20px; left: 20px; color: white; font-family: monospace; }
  </style>
</head>
<body>
  <div class="controls">
    <button onclick="prevSeed()">Prev</button>
    <span id="seedDisplay">Seed: 0</span>
    <button onclick="nextSeed()">Next</button>
    <button onclick="randomSeed()">Random</button>
  </div>
  <script>
    // Your generative algorithm here
  </script>
</body>
</html>

Common Generative Techniques

Particle Systems:

class Particle {
  constructor(x, y) {
    this.pos = createVector(x, y);
    this.vel = p5.Vector.random2D().mult(random(1, 3));
    this.life = 255;
  }

  update() {
    this.pos.add(this.vel);
    this.life -= 2;
  }

  draw() {
    noStroke();
    fill(255, this.life);
    circle(this.pos.x, this.pos.y, 4);
  }
}

Flow Fields:

function flowField(x, y, scale) {
  let angle = noise(x * scale, y * scale) * TWO_PI * 2;
  return p5.Vector.fromAngle(angle);
}

Recursive Subdivision:

function subdivide(x, y, w, h, depth) {
  if (depth === 0 || random() < 0.2) {
    rect(x, y, w, h);
    return;
  }

  if (random() < 0.5) {
    let split = random(0.3, 0.7) * w;
    subdivide(x, y, split, h, depth - 1);
    subdivide(x + split, y, w - split, h, depth - 1);
  } else {
    let split = random(0.3, 0.7) * h;
    subdivide(x, y, w, split, depth - 1);
    subdivide(x, y + split, w, h - split, depth - 1);
  }
}

Color Palettes

const palettes = {
  midnight: ['#0d1b2a', '#1b263b', '#415a77', '#778da9', '#e0e1dd'],
  sunset: ['#ff6b6b', '#feca57', '#48dbfb', '#ff9ff3', '#54a0ff'],
  forest: ['#2d3436', '#636e72', '#b2bec3', '#dfe6e9', '#00b894'],
  ocean: ['#0a3d62', '#1e5f74', '#289672', '#38ada9', '#82ccdd'],
};

Output

Every artwork produces:

  1. Markdown explaining the generative aesthetic philosophy
  2. Single HTML artifact containing algorithm, UI, and all functionality

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.

Check your setup, free