1Password에 저장한 비밀번호와 API 키를 명령과 설정 템플릿에 사용합니다. CLI 설치와 인증부터 비밀 값 조회 및 환경 변수 전달까지 안내합니다.
- 1Password CLI 설치와 설정
- 저장된 API 키로 명령 실행
- 설정 템플릿에 비밀 값 삽입
p5.js로 브라우저에서 실행되는 생성 예술과 조작이나 소리에 반응하는 영상을 만듭니다. 구상부터 구현, 화면 확인, 이미지와 동영상 내보내기까지 진행합니다.
p5.js sketches: gen art, shaders, interactive, 3D.
p5.js로 브라우저에서 실행되는 예술 작품과 애니메이션을 제작합니다. 규칙이나 난수로 만드는 생성 예술, 데이터 시각화, 마우스나 소리에 반응하는 표현, 입체 장면을 다룹니다. 구상을 정하고 색상, 움직임, 조작 방식을 설계한 뒤 HTML을 구현해 화면을 확인합니다. PNG, GIF, MP4, SVG 등으로 내보내는 과정도 다룹니다.
입자가 흐르는 배경, 조작에 따라 변하는 작품, 음악에 맞춰 움직이는 영상을 만들 때 활용합니다. 생성의 시작점을 정하는 시드 값으로 같은 작품을 재현할 수 있습니다. 슬라이더로 움직임이나 밀도를 조절하는 화면도 만들 수 있습니다.
기본적으로 단일 HTML 파일과 CDN의 p5.js를 사용합니다. 로컬 이미지나 글꼴을 읽으려면 서버가 필요합니다. 자동 고해상도 출력에는 Node.js와 Puppeteer를, MP4에는 ffmpeg를 사용합니다. SVG용 p5.js-svg는 p5.js 1.x가 필요하며, p5.brush는 p5.js 2.x와 WEBGL이 필요합니다.
이 소개문은 공개된 SKILL.md를 바탕으로 AI(OpenAI Codex)가 작성했습니다. 정확한 사양은 아래 원문을 확인하세요.
AI가 SKILL.md의 내용만을 근거로 4가지 관점에서 판정했습니다. 스타 수나 인기도는 판정에 넣지 않았습니다.
총점은 각 항목을 A=25점, B=15점, C=5점으로 더한 값입니다. 2026년 10월 19일 기준으로 AI(OpenAI Codex)가 판정했습니다. 참고용이므로 설치 전에 원문도 확인해 주세요.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems, flow fields, shaders (GLSL), pixel manipulation, kinetic typography, WebGL scenes, audio analysis, mouse/keyboard interaction, and headless high-res export.
This is visual art rendered in the browser. The canvas is the medium; the algorithm is the brush.
Before writing a single line of code, articulate the creative concept. What does this piece communicate? What makes the viewer stop scrolling? What separates this from a code tutorial example? The user's prompt is a starting point — interpret it with creative ambition.
First-render excellence is non-negotiable. The output must be visually striking on first load. If it looks like a p5.js tutorial exercise, a default configuration, or "AI-generated creative coding," it is wrong. Rethink before shipping.
Go beyond the reference vocabulary. The noise functions, particle systems, color palettes, and shader effects in the references are a starting vocabulary. For every project, combine, layer, and invent. The catalog is a palette of paints — you write the painting.
Be proactively creative. If the user asks for "a particle system," deliver a particle system with emergent flocking behavior, trailing ghost echoes, palette-shifted depth fog, and a background noise field that breathes. Include at least one visual detail the user didn't ask for but will appreciate.
Dense, layered, considered. Every frame should reward viewing. Never flat white backgrounds. Always compositional hierarchy. Always intentional color. Always micro-detail that only appears on close inspection.
Cohesive aesthetic over feature count. All elements must serve a unified visual language — shared color temperature, consistent stroke weight vocabulary, harmonious motion speeds. A sketch with ten unrelated effects is worse than one with three that belong together.
| Mode | Input | Output | Reference |
|---|---|---|---|
| Generative art | Seed / parameters | Procedural visual composition (still or animated) | references/visual-effects.md |
| Data visualization | Dataset / API | Interactive charts, graphs, custom data displays | references/interaction.md |
| Interactive experience | None (user drives) | Mouse/keyboard/touch-driven sketch | references/interaction.md |
| Animation / motion graphics | Timeline / storyboard | Timed sequences, kinetic typography, transitions | references/animation.md |
| 3D scene | Concept description | WebGL geometry, lighting, camera, materials | references/webgl-and-3d.md |
| Image processing | Image file(s) | Pixel manipulation, filters, mosaic, pointillism | references/visual-effects.md § Pixel Manipulation |
| Audio-reactive | Audio file / mic | Sound-driven generative visuals | references/interaction.md § Audio Input |
Single self-contained HTML file per project. No build step required.
| Layer | Tool | Purpose |
|---|---|---|
| Core | p5.js 1.11.3 (CDN) | Canvas rendering, math, transforms, event handling |
| 3D | p5.js WebGL mode | 3D geometry, camera, lighting, GLSL shaders |
| Audio | p5.sound.js (CDN) | FFT analysis, amplitude, mic input, oscillators |
| Export | Built-in saveCanvas() / saveGif() / saveFrames() | PNG, GIF, frame sequence output |
| Capture | CCapture.js (optional) | Deterministic framerate video capture (WebM, GIF) |
| Headless | Puppeteer + Node.js (optional) | Automated high-res rendering, MP4 via ffmpeg |
| SVG | p5.js-svg 1.6.0 (optional) | Vector output for print — requires p5.js 1.x |
| Natural media | p5.brush (optional) | Watercolor, charcoal, pen — requires p5.js 2.x + WEBGL |
| Texture | p5.grain (optional) | Film grain, texture overlays |
| Fonts | Google Fonts / loadFont() | Custom typography via OTF/TTF/WOFF2 |
p5.js 1.x (1.11.3) is the default — stable, well-documented, broadest library compatibility. Use this unless a project requires 2.x features.
p5.js 2.x (2.2+) adds: async setup() replacing preload(), OKLCH/OKLAB color modes, splineVertex(), shader .modify() API, variable fonts, textToContours(), pointer events. Required for p5.brush. See references/core-api.md § p5.js 2.0.
Every project follows the same 6-stage path:
CONCEPT → DESIGN → CODE → PREVIEW → EXPORT → VERIFY
preload() → setup() → draw() → helpers → classes → event handlerssaveCanvas() for PNG, saveGif() for GIF, saveFrames() + ffmpeg for MP4, Puppeteer for headless batch| Dimension | Options | Reference |
|---|---|---|
| Color system | HSB/HSL, RGB, named palettes, procedural harmony, gradient interpolation | references/color-systems.md |
| Noise vocabulary | Perlin noise, simplex, fractal (octaved), domain warping, curl noise | references/visual-effects.md § Noise |
| Particle systems | Physics-based, flocking, trail-drawing, attractor-driven, flow-field following | references/visual-effects.md § Particles |
| Shape language | Geometric primitives, custom vertices, bezier curves, SVG paths | references/shapes-and-geometry.md |
| Motion style | Eased, spring-based, noise-driven, physics sim, lerped, stepped | references/animation.md |
| Typography | System fonts, loaded OTF, textToPoints() particle text, kinetic | references/typography.md |
| Shader effects | GLSL fragment/vertex, filter shaders, post-processing, feedback loops | references/webgl-and-3d.md § Shaders |
| Composition | Grid, radial, golden ratio, rule of thirds, organic scatter, tiled | references/core-api.md § Composition |
| Interaction model | Mouse follow, click spawn, drag, keyboard state, scroll-driven, mic input | references/interaction.md |
| Blend modes | BLEND, ADD, MULTIPLY, SCREEN, DIFFERENCE, EXCLUSION, OVERLAY | references/color-systems.md § Blend Modes |
| Layering | createGraphics() offscreen buffers, alpha compositing, masking | references/core-api.md § Offscreen Buffers |
| Texture | Perlin surface, stippling, hatching, halftone, pixel sorting | references/visual-effects.md § Texture Generation |
Never use default configurations. For every project:
fill(255, 0, 0). Always a designed palette with 3-7 colorsbackground(0) or background(255). Always textured, gradient, or layeredFor every project, invent at least one of:
Parameters should emerge from the algorithm, not from a generic menu. Ask: "What properties of this system should be tunable?"
Good parameters expose the algorithm's character:
Bad parameters are generic controls unrelated to the algorithm:
Every parameter should change how the algorithm thinks, not just how it looks. A "turbulence" parameter that changes noise octaves is good. A "particle size" slider that only changes ellipse() radius is shallow.
Before any code, articulate:
Map the user's prompt to aesthetic choices. "Relaxing generative background" demands different everything from "glitch data visualization."
windowWidth/windowHeightP2D (default) or WEBGL (for 3D, shaders, advanced blend modes)noLoop() (static generative)templates/viewer.html which provides seed navigation, parameter sliders, and download. For simple sketches or video export, use bare HTMLFor interactive generative art (seed exploration, parameter tuning): start from templates/viewer.html. Read the template first, keep the fixed sections (seed nav, actions), replace the algorithm and parameter controls. This gives the user seed prev/next/random/jump, parameter sliders with live update, and PNG download — all wired up.
For animations, video export, or simple sketches: use bare HTML:
Single HTML file. Structure:
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Project Name</title>
<script>p5.disableFriendlyErrors = true;</script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.11.3/p5.min.js"></script>
<!-- <script src="https://cdnjs.cloudflare.com/ajax/libs/p5.js/1.11.3/addons/p5.sound.min.js"></script> -->
<!-- <script src="https://unpkg.com/p5.js-svg@1.6.0"></script> --> <!-- SVG export -->
<!-- <script src="https://cdn.jsdelivr.net/npm/ccapture.js-npmfixed/build/CCapture.all.min.js"></script> --> <!-- video capture -->
<style>
html, body { margin: 0; padding: 0; overflow: hidden; }
canvas { display: block; }
</style>
</head>
<body>
<script>
// === Configuration ===
const CONFIG = {
seed: 42,
// ... project-specific params
};
// === Color Palette ===
const PALETTE = {
bg: '#0a0a0f',
primary: '#e8d5b7',
// ...
};
// === Global State ===
let particles = [];
// === Preload (fonts, images, data) ===
function preload() {
// font = loadFont('...');
}
// === Setup ===
function setup() {
createCanvas(1920, 1080);
randomSeed(CONFIG.seed);
noiseSeed(CONFIG.seed);
colorMode(HSB, 360, 100, 100, 100);
// Initialize state...
}
// === Draw Loop ===
function draw() {
// Render frame...
}
// === Helper Functions ===
// ...
// === Classes ===
class Particle {
// ...
}
// === Event Handlers ===
function mousePressed() { /* ... */ }
function keyPressed() { /* ... */ }
function windowResized() { resizeCanvas(windowWidth, windowHeight); }
</script>
</body>
</html>
Key implementation patterns:
randomSeed() + noiseSeed() for reproducibilitycolorMode(HSB, 360, 100, 100, 100) for intuitive color controlupdate() + display() methodscreateGraphics() for layered composition, trails, masksloadImage()/loadFont() from local files: use scripts/serve.sh or python -m http.server| Format | Method | Command |
|---|---|---|
| PNG | saveCanvas('output', 'png') in keyPressed() | Press 's' to save |
| High-res PNG | Puppeteer headless capture | node scripts/export-frames.js sketch.html --width 3840 --height 2160 --frames 1 |
| GIF | saveGif('output', 5) — captures N seconds | Press 'g' to save |
| Frame sequence | saveFrames('frame', 'png', 10, 30) — 10s at 30fps | Then ffmpeg -i frame-%04d.png -c:v libx264 output.mp4 |
| MP4 | Puppeteer frame capture + ffmpeg | bash scripts/render.sh sketch.html output.mp4 --duration 30 --fps 30 |
| SVG | createCanvas(w, h, SVG) with p5.js-svg | save('output.svg') |
The Friendly Error System (FES) adds up to 10x overhead. Disable it in every production sketch:
p5.disableFriendlyErrors = true; // BEFORE setup()
function setup() {
pixelDensity(1); // prevent 2x-4x overdraw on retina
createCanvas(1920, 1080);
}
In hot loops (particles, pixel ops), use Math.* instead of p5 wrappers — measurably faster:
// In draw() or update() hot paths:
let a = Math.sin(t); // not sin(t)
let r = Math.sqrt(dx*dx+dy*dy); // not dist() — or better: skip sqrt, compare magSq
let v = Math.random(); // not random() — when seed not needed
let m = Math.min(a, b); // not min(a, b)
Never console.log() inside draw(). Never manipulate DOM in draw(). See references/troubleshooting.md § Performance.
Every generative sketch must be reproducible. Same seed, same output.
function setup() {
randomSeed(CONFIG.seed);
noiseSeed(CONFIG.seed);
// All random() and noise() calls now deterministic
}
Never use Math.random() for generative content — only for performance-critical non-visual code. Always random() for visual elements. If you need a random seed: CONFIG.seed = floor(random(99999)).
For generative art platforms, replace p5's PRNG with the platform's deterministic random:
// fxhash convention
const SEED = $fx.hash; // unique per mint
const rng = $fx.rand; // deterministic PRNG
$fx.features({ palette: 'warm', complexity: 'high' });
// In setup():
randomSeed(SEED); // for p5's noise()
noiseSeed(SEED);
// Replace random() with rng() for platform determinism
let x = rng() * width; // instead of random(width)
See references/export-pipeline.md § Platform Export.
HSB (Hue, Saturation, Brightness) is dramatically easier to work with than RGB for generative art:
colorMode(HSB, 360, 100, 100, 100);
// Now: fill(hue, sat, bri, alpha)
// Rotate hue: fill((baseHue + offset) % 360, 80, 90)
// Desaturate: fill(hue, sat * 0.3, bri)
// Darken: fill(hue, sat, bri * 0.5)
Never hardcode raw RGB values. Define a palette object, derive variations procedurally. See references/color-systems.md.
Raw noise(x, y) looks like smooth blobs. Layer octaves for natural texture:
function fbm(x, y, octaves = 4) {
let val = 0, amp = 1, freq = 1, sum = 0;
for (let i = 0; i < octaves; i++) {
val += noise(x * freq, y * freq) * amp;
sum += amp;
amp *= 0.5;
freq *= 2;
}
return val / sum;
}
For flowing organic forms, use domain warping: feed noise output back as noise input coordinates. See references/visual-effects.md.
Flat single-pass rendering looks flat. Use offscreen buffers for composition:
let bgLayer, fgLayer, trailLayer;
function setup() {
createCanvas(1920, 1080);
bgLayer = createGraphics(width, height);
fgLayer = createGraphics(width, height);
trailLayer = createGraphics(width, height);
}
function draw() {
renderBackground(bgLayer);
renderTrails(trailLayer); // persistent, fading
renderForeground(fgLayer); // cleared each frame
image(bgLayer, 0, 0);
image(trailLayer, 0, 0);
image(fgLayer, 0, 0);
}
p5.js draw calls are expensive. For thousands of particles:
// SLOW: individual shapes
for (let p of particles) {
ellipse(p.x, p.y, p.size);
}
// FAST: single shape with beginShape()
beginShape(POINTS);
for (let p of particles) {
vertex(p.x, p.y);
}
endShape();
// FASTEST: pixel buffer for massive counts
loadPixels();
for (let p of particles) {
let idx = 4 * (floor(p.y) * width + floor(p.x));
pixels[idx] = r; pixels[idx+1] = g; pixels[idx+2] = b; pixels[idx+3] = 255;
}
updatePixels();
See references/troubleshooting.md § Performance.
Global mode pollutes window. For production, use instance mode:
const sketch = (p) => {
p.setup = function() {
p.createCanvas(800, 800);
};
p.draw = function() {
p.background(0);
p.ellipse(p.mouseX, p.mouseY, 50);
};
};
new p5(sketch, 'canvas-container');
Required when embedding multiple sketches on one page or integrating with frameworks.
createCanvas(w, h, WEBGL) — origin is center, not top-lefttranslate(-width/2, -height/2) to get P2D-like coordinatespush()/pop() around every transform — matrix stack overflows silentlytexture() before rect()/plane() — not aftercreateShader(vert, frag) — test on multiple browsersEvery sketch should include these in keyPressed():
function keyPressed() {
if (key === 's' || key === 'S') saveCanvas('output', 'png');
if (key === 'g' || key === 'G') saveGif('output', 5);
if (key === 'r' || key === 'R') { randomSeed(millis()); noiseSeed(millis()); }
if (key === ' ') CONFIG.paused = !CONFIG.paused;
}
For headless rendering via Puppeteer, the sketch must use noLoop() in setup. Without it, p5's draw loop runs freely while screenshots are slow — the sketch races ahead and you get skipped/duplicate frames.
function setup() {
createCanvas(1920, 1080);
pixelDensity(1);
noLoop(); // capture script controls frame advance
window._p5Ready = true; // signal readiness to capture script
}
The bundled scripts/export-frames.js detects _p5Ready and calls redraw() once per capture for exact 1:1 frame correspondence. See references/export-pipeline.md § Deterministic Capture.
For multi-scene videos, use the per-clip architecture: one HTML per scene, render independently, stitch with ffmpeg -f concat. See references/export-pipeline.md § Per-Clip Architecture.
When building p5.js sketches:
open sketch.html (macOS) or xdg-open sketch.html (Linux)python -m http.server 8080 in the project directory, then open http://localhost:8080/sketch.htmlkeyPressed() shortcuts as shown above, tell the user which key to pressnode scripts/export-frames.js sketch.html --frames 300 for automated frame capture (sketch must use noLoop() + _p5Ready)bash scripts/render.sh sketch.html output.mp4 --duration 30skill_view(name="p5js", file_path="references/...") to load specific reference files as needed during implementation| Metric | Target |
|---|---|
| Frame rate (interactive) | 60fps sustained |
| Frame rate (animated export) | 30fps minimum |
| Particle count (P2D shapes) | 5,000-10,000 at 60fps |
| Particle count (pixel buffer) | 50,000-100,000 at 60fps |
| Canvas resolution | Up to 3840x2160 (export), 1920x1080 (interactive) |
| File size (HTML) | < 100KB (excluding CDN libraries) |
| Load time | < 2s to first frame |
| File | Contents |
|---|---|
references/core-api.md | Canvas setup, coordinate system, draw loop, push()/pop(), offscreen buffers, composition patterns, pixelDensity(), responsive design |
references/shapes-and-geometry.md | 2D primitives, beginShape()/endShape(), Bezier/Catmull-Rom curves, vertex() systems, custom shapes, p5.Vector, signed distance fields, SVG path conversion |
references/visual-effects.md | Noise (Perlin, fractal, domain warp, curl), flow fields, particle systems (physics, flocking, trails), pixel manipulation, texture generation (stipple, hatch, halftone), feedback loops, reaction-diffusion |
references/animation.md | Frame-based animation, easing functions, lerp()/map(), spring physics, state machines, timeline sequencing, millis()-based timing, transition patterns |
references/typography.md | text(), loadFont(), textToPoints(), kinetic typography, text masks, font metrics, responsive text sizing |
references/color-systems.md | colorMode(), HSB/HSL/RGB, lerpColor(), paletteLerp(), procedural palettes, color harmony, blendMode(), gradient rendering, curated palette library |
references/webgl-and-3d.md | WEBGL renderer, 3D primitives, camera, lighting, materials, custom geometry, GLSL shaders (createShader(), createFilterShader()), framebuffers, post-processing |
references/interaction.md | Mouse events, keyboard state, touch input, DOM elements, createSlider()/createButton(), audio input (p5.sound FFT/amplitude), scroll-driven animation, responsive events |
references/export-pipeline.md | saveCanvas(), saveGif(), saveFrames(), deterministic headless capture, ffmpeg frame-to-video, CCapture.js, SVG export, per-clip architecture, platform export (fxhash), video gotchas |
references/troubleshooting.md | Performance profiling, per-pixel budgets, common mistakes, browser compatibility, WebGL debugging, font loading issues, pixel density traps, memory leaks, CORS |
templates/viewer.html | Interactive viewer template: seed navigation (prev/next/random/jump), parameter sliders, download PNG, responsive canvas. Start from this for explorable generative art |
If the user asks for creative, experimental, surprising, or unconventional output, select the strategy that best fits and reason through its steps BEFORE generating code.
Take a known generative pattern (flow field, particle system, L-system, cellular automata) and systematically transform it:
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
1Password에 저장한 비밀번호와 API 키를 명령과 설정 템플릿에 사용합니다. CLI 설치와 인증부터 비밀 값 조회 및 환경 변수 전달까지 안내합니다.
손익계산서·재무상태표·현금흐름표를 수식으로 연결한 Excel 모델을 만듭니다. 실적과 예측 가정을 입력하고 시나리오를 비교하며 세 재무제표의 일관성을 단계별로 확인합니다.
기존 PyTorch 학습 코드를 적은 수정으로 여러 GPU나 컴퓨터에 맞게 구성합니다. 혼합 정밀도, 메모리 절약 설정과 학습 실행 방법을 안내합니다.
Hermes에서 Actual Computer로 자신의 기기에 AI 모델을 실행하도록 연결을 설정합니다. 중계 서비스와 로컬 연결, 모델 선택, 응답 확인 및 오류 점검을 다룹니다.
기술에 익숙하지 않고 쉽게 불만을 느끼는 사용자로 앱을 시험합니다. 혼란스러운 조작과 이탈 원인을 찾고, 개선 과제와 개인적 불만을 나눠 수정안을 정리합니다.
두 에이전트가 각각 수정한 브랜치의 Git 충돌을 양쪽 변경 내용과 의도에 따라 중립적으로 해결합니다. 충돌별 판단 이유를 기록하고 빌드나 테스트로 통합 결과를 확인합니다.