algorithmic-art

Generates seeded p5.js generative art with interactive parameter controls in self-contained HTML.

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/leonardoacosta/agents --skill algorithmic-art-leonardoacosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: algorithmic-art
Source: https://github.com/leonardoacosta/agents/tree/main/skills/algorithmic-art
Command: npx skills add https://github.com/leonardoacosta/agents --skill algorithmic-art-leonardoacosta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating original generative art requires both a coherent aesthetic concept and working code; this Skill bridges that gap by first authoring an algorithmic philosophy and then expressing it as a reproducible p5.js artwork. ## Core Features & Use Cases - Algorithmic Philosophy Authoring: Produces a 4-6 paragraph generative art manifesto (.md) that guides the visual direction before any code is written. - Seeded p5.js Generation: Builds flow fields, particle systems, and noise-driven compositions with seeded randomness so every seed reproduces identical output. - Interactive Viewer: Outputs a single self-contained HTML artifact with seed navigation (prev/next/random/jump), parameter sliders, color pickers, and reset/download actions based on a fixed Anthropic-branded template. - Use Case: Ask for a generative artwork inspired by ocean currents, and receive a philosophy document plus an interactive HTML piece where you explore 100 seed variations and tune particle count, noise scale, and flow speed live. ## Quick Start Create an algorithmic art piece about emergent flocking behavior with an interactive viewer I can open in my browser.

Frequently Asked Questions about algorithmic-art

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create generative art with p5.js?

Define a seeded parameter object, call randomSeed and noiseSeed in setup for reproducibility, then implement your algorithm in setup and draw. This Skill wraps that process by first writing an algorithmic philosophy, then expressing it as a self-contained HTML artifact with interactive controls.

How do I make p5.js output reproducible with seeds?

Call randomSeed(seed) and noiseSeed(seed) before any random or noise calls so every run with the same seed produces identical output. The generated viewer includes prev, next, random, and jump-to-seed controls for exploring variations.

Does the generated art work in a browser without a server?

Yes, the output is a single self-contained HTML file with p5.js loaded from a CDN and all code inline. It runs immediately in any browser or as a claude.ai artifact with no build step or local server required.

What kinds of generative algorithms can this produce?

The Skill supports flow fields, particle systems, recursive branching, Voronoi tessellation, circle packing, and harmonic interference patterns. The specific algorithm is derived from the algorithmic philosophy written for each request rather than from a fixed pattern menu.

Can I customize the parameters and colors of the artwork?

Yes, the viewer template includes a Parameters section with sliders for numeric values and an optional Colors section with color pickers. Parameter ranges, control types, and palette choices are defined per artwork based on what the algorithm needs.