Skills Explorer Add Skills

algorithmic-art

An agent skill by anthropics, from anthropics/skills. Tags: anthropic, design, developer-tools, generative, visual-art, web.

What it does

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add anthropics/skills --skill algorithmic-art

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/anthropics/skills
cp -r skills/skills/algorithmic-art ~/.claude/skills/algorithmic-art

Safety box score

Grade B, low risk: 19 of 100 risk points, rated 2026-09-22. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill generates self-contained browser art artifacts in HTML/JS using p5.js, plus a short philosophy markdown file. The main risks are modest: the resulting page runs JavaScript in the browser and pulls a couple of third-party assets from public CDNs.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)It produces inline p5.js code with `setup()`/`draw()` inside HTML, but it does not ship shell commands, native binaries, or host-side code execution.
Network access1 (low)`templates/viewer.html` loads `https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.7.0/p5.min.js` and Google Fonts, so opening the artifact makes outbound requests.
Filesystem reach1 (low)The skill outputs `.md`, `.html`, and `.js` artifacts and is intended to stay self-contained; there is no evidence of reads/writes outside the working directory.
Secrets & credentials0 (none)No tokens, passwords, `.env` files, keychains, or CLI logins are referenced or requested.
Privilege & persistence0 (none)There are no `sudo`, global installs, service registrations, shell profile edits, or other privilege changes.
Instruction hijack surface1 (low)The files contain extensive model-facing instructions and HTML comments (including the hidden comment noted by the scan), but nothing that tells the agent to ignore safety rules or fetch external instructions.
Irreversible actions0 (none)The skill only creates generative art files; it does not publish, send, delete, deploy, pay, or book anything.
Transparency1 (low)The artifact depends on remote, externally hosted assets rather than bundled source, so behavior partly rests on third-party CDN content.

Before installing

Rated 2026-09-22 by an automated review of 4 files from the skill's repository.

Source

Repository
anthropics/skills (all skills from this repository)
Path
skills/algorithmic-art/SKILL.md
Branch
main
Updated
2026-09-19