Algorithmic Art

Create generative art with reproducible seeds and parameters, and explore visual variations.

Available in app
Concentric paper ribbons form a violet and cyan generative sculpture.

Overview

Generative art where the seed is law. Write a computational philosophy — what emerges from which process, where order and chaos pull — then deduce the conceptual seed from your brief and generate on the built-in algorithms. You receive a matched set: an interactive web piece (swap seeds, tune parameters and palettes, switch algorithms, download an image — one self-contained file that works offline), a static render of the same seed, and the saved generation parameters so the piece re-runs exactly from its seed.

A new seed is a sister piece; the same seed is always the same piece. New philosophies can extend the core with fresh algorithms.

On-screen behavior is judged by actually opening and capturing the page in the app — a correct numeric core isn't the same as the visible result, and what you see is what ships.

Where it helps

  • Turn an aesthetic one-liner into a tunable interactive piece plus static renders
  • Build a reproducible seed series for a brand — same recipe, sister pieces
  • Compare the two built-in algorithms' personalities under one parameter set
  • Save generation parameters so any piece can be exactly reproduced
#art#generative#html#seed#p5

Examples

Examples describe the request and the shape of the expected deliverable; they are not completed run results.

Example prompt

Philosophy 'tidal breathing': flowfield, 1200x1200, seed 987654321 — ship the interactive piece and static render, then three neighboring seeds at the same parameters as a comparison sheet.

Expected output

The full file set (interactive page, static render, parameters); rerunning the seed reproduces the identical piece.

Example prompt

Open the piece in the app: exercise the sliders and seed switches, then give me one actually-rendered screenshot — screen truth decides.

Expected output

An interaction walkthrough plus one genuine rendered screenshot; numeric self-checks and screen verification reported separately.

Requirements and limits

Install platforms
iOS
Script runtime
Runs scripts in the task environment
Minimum app version
1.7.62
Reviewed permission scope
Capabilities
Interact with web pagesObserve web pagesRemote executionRead workspace filesWrite workspace files
Reviewed tools
browser.click · browser.exportFile · browser.navigate · browser.observe · browser.screenshot · exec.localService · Shell commands · jobs.cancel · jobs.result · jobs.status · jobs.submit · workspace.publishOutput
Review decision
Approved
Review stage
Guest execution qualification
Reviewed on
2026-10-27
Implementation and runtime details
Adaptation stage
frozen
Tools
browser.click · browser.exportFile · browser.navigate · browser.observe · browser.screenshot · exec.localService · Shell commands · jobs.cancel · jobs.result · jobs.status · jobs.submit · workspace.publishOutput
Capabilities
Interact with web pagesObserve web pagesRemote executionRead workspace filesWrite workspace files
Runtime environment
linux / riscv64 · guest-verified

License and source

Source and trace details

License

Apache-2.0

Apache-2.0 (per-skill LICENSE.txt)

Pinned per-skill Apache-2.0 license preserved; Floe renderer code is separately identified as MPL-2.0. Bundled font faces, where present, retain their full SIL OFL notices and exact hashes.

Image and material attribution

Image attribution
Floe original, AI-assisted illustration.
Source
https://github.com/anthropics/skills
Upstream path
skills/algorithmic-art
Upstream pin
dbd4588f9e
Source checked
2026-10-26
Publisher
JiangNanGenius
Publication commit (retrieval)
25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
Audited source commit
84c524b6fb483e4cad94db076e7d9c9962966c19
Signed catalog digest
iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
Publication snapshot (UTC)
2026-10-31

Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….

Versions and status

Version records ship with the signed catalog; the target and released versions are shown below.

Adaptation
Ready
Publication state
Curated skills are available
Deep adaptation
Yes
Released version
iOS 1.1.0