Agent skill

Particles

by autonomous-ai in autonomous-ai/openharness

A skill your agent uses when creating particle effects in Phaser 4.

MITAuto-check passedGame Development

Install Particles

skills CLI
$ npx skills add autonomous-ai/openharness --skill particles -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autonomous-ai/openharness particles --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/phaser/skills/particles .claude/skills/particles && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
particles
GitHub stars
1.1k
Token cost
~5.2k tokens
SKILL.md length
1,288 words
Files
2 (incl. references)
Skills in repo
99
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when creating particle effects in Phaser 4.

  • Creating particle effects in Phaser 4
  • SKILL.md covers Quick Start, Core Concepts, Common Patterns and Configuration Reference, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Particle effect

What it does

Particles is an agent skill from autonomous-ai/openharness. Use this skill when creating particle effects in Phaser 4. Covers ParticleEmitter, emission zones, death zones, particle properties, textures, gravity wells, and particle movement. Triggers on: particles, emitter, particle effect, explosion, fire, smoke.

Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/REFERENCE.md`).

It sits in Game Development. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.

When your agent uses it

  • Creating particle effects in Phaser 4
  • Particle effect

Example prompts

  • “/particles”

What it can do on your machine

Read from SKILL.md and the folder at commit 54a1f1b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Particles loads about 5.2k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 1,288 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~5.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from autonomous-ai/openharness at commit 54a1f1b, republished under its MIT licence (© autonomous-ai). 1,288 words, ~5,193 tokens.

Download SKILL.mdSave it as .claude/skills/particles/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
particles
description
Use this skill when creating particle effects in Phaser 4. Covers ParticleEmitter, emission zones, death zones, particle properties, textures, gravity wells, and particle movement. Triggers on: particles, emitter, particle effect, explosion, fire, smoke.

Particle System

Creating and controlling particle effects in Phaser 4 -- ParticleEmitter creation and configuration, emitter ops (value formats), gravity wells, emission and death zones, flow vs burst modes, following game objects, and particle callbacks.

Key source paths: src/gameobjects/particles/ Related skills: ../sprites-and-images/SKILL.md, ../loading-assets/SKILL.md

Quick Start

js
// In a Scene's create() method:

// Basic continuous emitter (flow mode)
const emitter = this.add.particles(400, 300, 'flares', {
    frame: 'red',
    speed: 200,
    lifespan: 2000,
    scale: { start: 1, end: 0 },
    alpha: { start: 1, end: 0 },
    gravityY: 150
});

// One-shot burst (explode mode)
const burst = this.add.particles(400, 300, 'flares', {
    frame: 'blue',
    speed: { min: 100, max: 300 },
    lifespan: 1000,
    scale: { start: 0.5, end: 0 },
    emitting: false   // don't auto-start
});
burst.explode(20);    // emit 20 particles at once

Core Concepts

ParticleEmitter

ParticleEmitter extends GameObject and is added directly to the display list. It is both a game object (positionable, scalable, maskable) and the emitter itself. There is no separate manager -- this.add.particles() returns a ParticleEmitter instance.

Factory signature:

js
this.add.particles(x, y, texture, config);
// x, y: world position (both optional, default 0)
// texture: string key or Texture instance
// config: ParticleEmitterConfig object (optional, can call setConfig later)

Mixins: AlphaSingle, BlendMode, Depth, Lighting, Mask, RenderNodes, ScrollFactor, Texture, Transform, Visible. So you can call setPosition(), setScale(), setDepth(), setBlendMode(), setMask(), setScrollFactor(), etc.

Particle

A lightweight object owned by its emitter. Key properties: x, y, velocityX/Y, accelerationX/Y, scaleX/Y, alpha, angle, rotation, tint, life (total ms), lifeCurrent (remaining ms), lifeT (0-1 normalized), bounce, delayCurrent, holdCurrent. Particles are pooled internally -- you never create them manually.

EmitterOp Value Formats

Most config properties (speed, scale, alpha, angle, x, y, etc.) accept flexible value formats:

js
x: 400                                        // static value
x: [100, 200, 300, 400]                       // random pick from array
x: { min: 100, max: 700 }                     // random float in range
x: { min: 100, max: 700, int: true }          // random integer
x: { random: [100, 700] }                     // random integer shorthand
scale: { start: 0, end: 1 }                   // ease over lifetime (default linear)
scale: { start: 0, end: 1, ease: 'bounce.out' }  // custom ease
scale: { start: 4, end: 0.5, random: true }   // random start, ease to end
x: { values: [50, 500, 200, 800], interpolation: 'catmull' }  // interpolation
x: { steps: 32, start: 0, end: 576 }          // stepped sequential
x: { steps: 32, start: 0, end: 576, yoyo: true }  // stepped with yoyo
x: {                                           // custom callbacks
    onEmit: (particle, key, t, value) => value,
    onUpdate: (particle, key, t, value) => value
}
x: (particle, key, t, value) => value + 50    // emit-time callback shorthand

Emit-only (no onUpdate): angle, delay, hold, lifespan, quantity, speedX, speedY. Emit + Update (support start/end, onUpdate): accelerationX/Y, alpha, bounce, maxVelocityX/Y, moveToX/Y, rotate, scaleX/Y, tint, x, y.

Flow vs Explode (Burst)

Flow mode (frequency >= 0): emits quantity particles every frequency ms. Default is frequency: 0 (every frame) with emitting: true.

Explode mode (frequency = -1): emits a batch all at once, then stops.

js
emitter.flow(100, 5);           // 5 particles every 100ms
emitter.flow(100, 5, 50);       // auto-stop after 50 total
emitter.explode(30, 200, 400);  // burst 30 at position
emitter.explode(30);            // burst at emitter position

Common Patterns

Scale, Alpha, and Color Over Lifetime
js
// Scale and alpha with custom easing
this.add.particles(400, 300, 'spark', {
    lifespan: 2000,
    speed: 100,
    scale: { start: 1, end: 0, ease: 'power2' },
    alpha: { start: 1, end: 0, ease: 'cubic.in' }
});
Color Interpolation

The color property interpolates through an array of colors over particle lifetime (overrides tint):

js
this.add.particles(400, 300, 'spark', {
    lifespan: 2000, speed: 100, scale: { start: 0.5, end: 0 },
    color: [0xfacc22, 0xf89800, 0xf83600, 0x9f0404], colorEase: 'quad.out'
});
Tinting Particles
js
this.add.particles(400, 300, 'spark', { tint: 0xff0000 });                           // static
this.add.particles(400, 300, 'spark', { tint: { start: 0xffffff, end: 0xff0000 } }); // over lifetime
Gravity Wells

A GravityWell applies inverse-square gravitational force, pulling (or repelling with negative power) particles toward a point.

js
const emitter = this.add.particles(400, 300, 'spark', {
    speed: 100, lifespan: 4000, scale: { start: 0.4, end: 0 }, quantity: 2
});

const well = emitter.createGravityWell({
    x: 400, y: 300, power: 2, epsilon: 100, gravity: 50
});

// Update at runtime
well.x = 300;
well.power = -1;  // negative = repel

// Or create manually and add
const well2 = new Phaser.GameObjects.Particles.GravityWell(500, 200, 3, 100, 50);
emitter.addParticleProcessor(well2);
emitter.removeParticleProcessor(well2);
Emission Zones (Random)

A RandomZone spawns particles at random positions within a shape. The source must have a getRandomPoint(point) method -- all Phaser geometry classes (Circle, Ellipse, Rectangle, Triangle, Polygon, Line) support this, or provide a custom source:

js
// Using built-in geometry
this.add.particles(400, 300, 'spark', {
    speed: 50, lifespan: 2000,
    emitZone: { type: 'random', source: new Phaser.Geom.Circle(0, 0, 100) }
});

// Custom source object (any object with getRandomPoint)
emitter.addEmitZone({
    type: 'random',
    source: {
        getRandomPoint: (point) => {
            const a = Math.random() * Math.PI * 2;
            point.x = Math.cos(a) * 100;
            point.y = Math.sin(a) * 50;
            return point;
        }
    }
});
Emission Zones (Edge)

An EdgeZone places particles sequentially along shape edges. The source must have a getPoints(quantity, stepRate) method. Curves, Paths, and all geometry shapes support this:

js
this.add.particles(400, 300, 'spark', {
    lifespan: 1500, speed: 20,
    emitZone: {
        type: 'edge',
        source: new Phaser.Geom.Circle(0, 0, 150),
        quantity: 48,     // number of points on edge (use 0 with stepRate instead)
        yoyo: false,      // reverse direction at ends
        seamless: true    // remove duplicate endpoint
    }
});

// Or add post-creation with any source that has getPoints
emitter.addEmitZone({ type: 'edge', source: geom, quantity: 50, yoyo: false, seamless: true });

Multiple emission zones: Pass an array to emitZone or call addEmitZone() multiple times. Zones iterate in sequence. The total property controls how many particles emit before rotating to the next zone (-1 = never rotate).

js
this.add.particles(400, 300, 'spark', {
    emitZone: [
        { type: 'random', source: new Phaser.Geom.Circle(0, 0, 50) },
        { type: 'random', source: new Phaser.Geom.Circle(200, 0, 50) }
    ]
});
Death Zones

A DeathZone kills particles when they enter (or leave) a region. The source must have a contains(x, y) method.

js
// Kill particles entering a rectangle
this.add.particles(400, 100, 'spark', {
    speed: 200, lifespan: 5000, gravityY: 100,
    deathZone: { type: 'onEnter', source: new Phaser.Geom.Rectangle(300, 400, 200, 50) }
});

// Kill particles leaving a circle (confine to area)
this.add.particles(400, 300, 'spark', {
    speed: 100, lifespan: 5000,
    deathZone: { type: 'onLeave', source: new Phaser.Geom.Circle(400, 300, 150) }
});

// Custom death zone source (any object with contains)
emitter.addDeathZone({
    type: 'onEnter',
    source: { contains: (x, y) => x > 600 && y > 400 }
});
Following a Game Object
js
const player = this.add.sprite(100, 100, 'player');
const emitter = this.add.particles(0, 0, 'spark', {
    speed: 50, lifespan: 800, scale: { start: 0.5, end: 0 }
});

emitter.startFollow(player);                       // follow position
emitter.startFollow(player, 10, -20);              // with offset
emitter.startFollow(player, 0, 0, true);           // track visibility too
emitter.stopFollow();

// Or via config:
this.add.particles(0, 0, 'spark', { follow: player, followOffset: { x: 0, y: -20 } });
Particle Callbacks
js
// Via config
const emitter = this.add.particles(400, 300, 'spark', {
    speed: 100, lifespan: 2000,
    emitCallback: (particle, emitter) => { /* on emit */ },
    deathCallback: (particle) => { /* on death */ }
});

// Or set after creation
emitter.onParticleEmit((particle, emitter) => { /* ... */ });
emitter.onParticleDeath((particle) => { /* ... */ });

// Iterate alive/dead particles
emitter.forEachAlive((particle, emitter) => { /* particle.x, particle.lifeT */ });
Duration, StopAfter, and Advance
js
// Auto-stop after 3 seconds (alive particles continue until they expire)
this.add.particles(400, 300, 'spark', { speed: 100, duration: 3000 });

// Emit exactly 50 particles then stop
this.add.particles(400, 300, 'spark', { speed: 100, stopAfter: 50 });

// Pre-warm: fast-forward 2 seconds so particles visible on first frame
this.add.particles(400, 300, 'spark', { speed: 100, lifespan: 2000, advance: 2000 });
// Or manually: emitter.fastForward(2000, 50);
Particle Bounds (Bounce)
js
this.add.particles(400, 300, 'spark', {
    speed: 200, lifespan: 5000, bounce: 0.8,
    bounds: { x: 100, y: 100, width: 600, height: 400 },
    collideLeft: true, collideRight: true, collideTop: true, collideBottom: true
});
// Or: emitter.addParticleBounds(100, 100, 600, 400);
Texture Frames and Animations
js
// Random frame per particle
this.add.particles(400, 300, 'flares', { frame: ['red', 'green', 'blue'] });

// Sequential frames cycling through with quantity per frame
this.add.particles(400, 300, 'flares', {
    frame: { frames: ['red', 'green', 'blue'], cycle: true, quantity: 4 }
});

// Particle animation (plays anim over particle lifetime)
this.add.particles(400, 300, 'explosion', { anim: 'explode_anim', lifespan: 1000 });

// Multiple anims, randomly assigned
this.add.particles(400, 300, 'sheet', {
    anim: { anims: ['fire', 'smoke'], cycle: false, quantity: 1 }
});
Sorting Particles
js
this.add.particles(400, 300, 'spark', { sortProperty: 'y', sortOrderAsc: true });
// Or: sortCallback: (a, b) => a.y - b.y
Custom Particle Processor

Extend ParticleProcessor to apply custom per-particle logic each frame. Implement update(particle, delta, step, t):

js
class WindProcessor extends Phaser.GameObjects.Particles.ParticleProcessor {
    constructor (windX, windY) {
        super(0, 0);
        this.windX = windX;
        this.windY = windY;
    }

    update (particle, delta, step, t) {
        particle.velocityX += this.windX * step;
        particle.velocityY += this.windY * step;
    }
}

emitter.addParticleProcessor(new WindProcessor(0.5, 0));
Custom Particle Class

Extend Particle and override update for per-particle behavior. Set via particleClass in config:

js
class TrailParticle extends Phaser.GameObjects.Particles.Particle {
    update (delta, step, processors) {
        const result = super.update(delta, step, processors);
        this.alpha = this.lifeT;  // custom: alpha matches life progress
        return result;  // must return true if particle is still alive
    }
}

this.add.particles(400, 300, 'spark', {
    particleClass: TrailParticle,
    speed: 100, lifespan: 2000
});

Configuration Reference

ParticleEmitterConfig -- Simple Properties
PropertyTypeDefaultDescription
activebooleantrueFalse = emitter does not update at all
emittingbooleantrueFalse = no new particles (alive ones still update)
blendModestring/number0Blend mode for rendering
frequencynumber0ms between flow cycles; 0 = every frame; -1 = explode
gravityX, gravityYnumber0Gravity in px/s^2
maxParticlesnumber0Hard limit on total particle objects (0 = unlimited)
maxAliveParticlesnumber0Max alive particles at once (0 = unlimited)
durationnumber0Auto-stop after ms (0 = forever)
stopAfternumber0Auto-stop after N particles emitted (0 = unlimited)
advancenumber0Fast-forward on creation (ms)
radialbooleantrueTrue = speed+angle; false = speedX/speedY
particleBringToTopbooleantrueNew particles render on top
timeScalenumber1Time multiplier for updates
followVector2LikenullObject to follow
followOffsetVector2LikeOffset from follow target
trackVisiblebooleanfalseMatch follow target's visibility
reservenumberPre-allocate particle objects
particleClassfunctionParticleCustom particle class
sortPropertystringParticle property to sort by
sortOrderAscbooleanSort ascending if true
ParticleEmitterConfig -- EmitterOp Properties

All accept the flexible value formats described above.

PropertyDefaultE/UDescription
x, y0E+UParticle offset from emitter
speed0ERadial speed (sets speedX, deactivates speedY)
speedX, speedY0EDirectional speed (sets radial=false)
angle{min:0,max:360}EEmission angle in degrees
scale1E+UUniform scale (sets scaleX, deactivates scaleY)
scaleX, scaleY1E+UNon-uniform scale
alpha1E+UAlpha transparency
rotate0E+URotation in degrees
tint0xffffffE+UTint color (WebGL)
colorE+UColor array to interpolate (overrides tint)
colorEaseEase for color interpolation
lifespan1000ELifetime in ms
delay0EDelay before visible (ms)
hold0EHold at end of life before dying (ms)
quantity1EParticles per flow cycle
accelerationX/Y0E+UAcceleration (px/s^2)
maxVelocityX/Y10000E+UMax velocity
bounce0E+UBounce restitution (0-1)
moveToX, moveToY0E+UTarget position (overrides angle/speed)

E = emit-only, E+U = emit + update (supports start/end, onUpdate)

Show full SKILL.md (529 more words)Show less
Zone Config Properties
Config KeyTypeProperties
emitZoneobject or array{ type: 'random', source: <shape> }
{ type: 'edge', source: <shape>, quantity, stepRate, yoyo, seamless, total }
deathZoneobject or array{ type: 'onEnter'|'onLeave', source: <shape> }
boundsobject{ x, y, width, height } or { x, y, w, h }

Events

All events are emitted on the ParticleEmitter instance itself.

EventStringCallback ArgsWhen
START'start'(emitter)start() is called and emitter begins emitting
STOP'stop'(emitter)stop() is called, or duration/stopAfter limit reached
COMPLETE'complete'(emitter)Final alive particle dies after emitter has stopped
EXPLODE'explode'(emitter, particle)explode() is called
DEATH_ZONE'deathzone'(emitter, particle, zone)A death zone kills a particle
js
emitter.on('stop', (emitter) => { /* stopped emitting */ });
emitter.on('complete', (emitter) => { /* all particles dead */ });
emitter.on('deathzone', (emitter, particle, zone) => { /* ... */ });

API Quick Reference

ParticleEmitter Key Methods

Lifecycle: start(advance?, duration?), stop(kill?), pause(), resume(), flow(frequency, count?, stopAfter?), explode(count?, x?, y?), emitParticleAt(x?, y?, count?), emitParticle(count?, x?, y?), fastForward(time, delta?).

Config: setConfig(config), updateConfig(config).

Following: startFollow(target, offX?, offY?, trackVisible?), stopFollow().

Zones: addEmitZone(config), removeEmitZone(zone), clearEmitZones(), addDeathZone(config), removeDeathZone(zone), clearDeathZones().

Processors: createGravityWell(config), addParticleProcessor(processor), removeParticleProcessor(processor), getProcessors().

Bounds: addParticleBounds(x, y, w, h, collideL?, collideR?, collideT?, collideB?).

Callbacks/Iteration: onParticleEmit(cb, ctx?), onParticleDeath(cb, ctx?), killAll(), forEachAlive(cb, ctx?), forEachDead(cb, ctx?).

Counts: getAliveParticleCount(), getDeadParticleCount(), getParticleCount(), atLimit(), reserve(count).

Property setters: setParticleSpeed(x, y?), setParticleScale(x, y?), setParticleGravity(x, y), setParticleAlpha(value), setParticleTint(value), setParticleLifespan(value), setEmitterAngle(value), setQuantity(qty), setFrequency(freq, qty?), setRadial(value), setEmitterFrame(frames, random?, qty?), setAnim(anims, random?, qty?).

Sorting: setSortProperty(property, ascending?), setSortCallback(callback), depthSort().

Utility: getBounds(padding?, advance?, delta?, output?), overlap(target).

GravityWell
Property/MethodDescription
x, yWorld position of the well
powerForce strength (negative to repel)
epsilonMin distance for force calc (default 100)
gravityGravitational constant (default 50)
activeEnable/disable processing (inherited from ParticleProcessor)

Constructor: new GravityWell(x, y, power, epsilon, gravity) or new GravityWell(config) where config is { x, y, power, epsilon, gravity }.

Gotchas

  • No ParticleEmitterManager: Removed in v3.60. this.add.particles() returns a ParticleEmitter directly.
  • speed vs speedX/speedY: speed sets speedX and deactivates speedY (radial). speedX/speedY switches to point mode (radial: false).
  • scale vs scaleX/scaleY: scale applies to scaleX and deactivates scaleY. Use both for non-uniform scaling.
  • color overrides tint: They are mutually exclusive; color (array) takes priority.
  • moveToX/moveToY: Both must be set to activate. Overrides angle and speed.
  • emitting vs active: emitting: false = no new particles but alive ones update. active: false = entire emitter frozen.
  • stop vs complete: 'stop' fires when emission stops. 'complete' fires when the last alive particle dies.
  • frequency: 0: Means emit every frame (max rate), not "never." Use emitting: false to prevent emission.
  • frequency: -1: Puts the emitter in explode mode -- it will not flow automatically. Use explode() to emit bursts.
  • hold freezes particle: After lifespan expires, hold keeps the particle visible and frozen for the specified ms before it dies. Useful for trail/lingering effects.
  • advance fast-forwards: Pre-warms the emitter by simulating the given ms on creation, so particles are already visible on the first frame.
  • reserve(count) pre-allocates: Call reserve() or set reserve in config to pre-create particle objects upfront, avoiding GC spikes during gameplay from on-demand allocation.
  • Zone source methods: RandomZone needs getRandomPoint(point). EdgeZone needs getPoints(quantity, stepRate). DeathZone needs contains(x, y).
  • Particle pool: maxParticles limits total objects (not alive count). Use maxAliveParticles for visible limit.
  • Texture required: The emitter needs a valid texture key. Use frame config for multi-frame textures.

Source Files

See references/REFERENCE.md for the full source file map. Key entry points: src/gameobjects/particles/ParticleEmitter.js (main class), src/gameobjects/particles/Particle.js (individual particle), src/gameobjects/particles/zones/ (zone classes).

© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in store/agents/phaser/skills/particles of autonomous-ai/openharness.

  • SKILL.md
  • references/REFERENCE.md

Open the folder on GitHubat commit 54a1f1b

Compare with similar skills

Particles next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Particles compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Particles this skillautonomous-ai/openharness1.1k—~5.2kAutomated safety check: PassMIT
Image to Three.js Modelimg2threejs/img2threejs18k1 repos~8.2kAutomated safety check: PassApache-2.0
Web CloneJane-xiaoer/claude-skill-web-clone1k1 repos~2.7kAutomated safety check: PassMIT
Threejs Game Directormajidmanzarpour/threejs-game-skills2.4k—~2.2kAutomated safety check: PassMIT
Game Asset Generatorhtdt/godogen7.1k—~2.8kAutomated safety check: PassMIT
Threejs Gameplay Systemsvalkor-ai/loom1.2k1 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Image to Three.js Model

    img2threejs/img2threejs

    Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.

    18k GitHub starsUsed in 1 repo~8.2k tokens
    Game DevelopmentAuto-check passed
  • Web Clone

    Jane-xiaoer/claude-skill-web-clone

    网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 /…

    1k GitHub starsUsed in 1 repo~2.7k tokens
    Game DevelopmentAuto-check passed
  • Threejs Game Director

    majidmanzarpour/threejs-game-skills

    Entrypoint for building, upgrading, and finishing Three.js browser games.

    2.4k GitHub stars~2.2k tokensUpdated 9 days ago
    Game DevelopmentAuto-check passed
  • Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.

    7.1k GitHub stars~2.8k tokensUpdated 5 days ago
    Game DevelopmentAuto-check passed
  • Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Game DevelopmentAuto-check passed
  • Uloop Execute Dynamic Code

    CyberAgentGameEntertainment/NovaShader

    Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.

    1.6k GitHub starsUsed in 1 repo~1.9k tokens
    Game DevelopmentAuto-check passed

More from autonomous-ai/openharness

All 99 skills in this repo
  • G-code Slicer Tool

    autonomous-ai/openharness

    Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.

    1.1k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Home Assistant Automation Builder

    autonomous-ai/openharness

    Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.

    1.1k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Score Music Composer

    autonomous-ai/openharness

    Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.

    1.1k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • OrcaSlicer 3MF and G-code Workflow

    autonomous-ai/openharness

    Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.

    1.1k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Sheets and Docs Report Builder

    autonomous-ai/openharness

    Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.

    1.1k GitHub stars~708 tokensUpdated today
    Auto-check passed
  • Bambu Labs

    autonomous-ai/openharness

    Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

    1.1k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about Particles

What does Particles do?

A skill your agent uses when creating particle effects in Phaser 4. Particles is an agent skill from autonomous-ai/openharness. Use this skill when creating particle effects in Phaser 4.

When should I use Particles?

Particles fits situations like: creating particle effects in Phaser 4; particle effect.

How do I install Particles in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill particles -a claude-code`. Or copy the skill folder (store/agents/phaser/skills/particles in autonomous-ai/openharness) into .claude/skills/particles in your project. Claude Code loads it when a task matches its description.

How do I install Particles in Codex?

Run `npx skills add autonomous-ai/openharness --skill particles -a codex`. Or copy the skill folder (store/agents/phaser/skills/particles in autonomous-ai/openharness) into .agents/skills/particles in your project. Codex loads it when a task matches its description.

Can I use Particles in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill particles -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/particles, .gemini/skills/particles, .github/skills/particles and .opencode/skills/particles in your project.

What does Particles need to run?

SKILL.md names no scripts, command-line tools or credentials: Particles is instructions for the agent only.

Does Particles access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Particles safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Particles use?

Particles is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Particles use?

About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 256 tokens, read only when the agent opens those files.

What are the alternatives to Particles?

Skills that share tags, products or a category with Particles: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.4k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Particles?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,137 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 7, 2026.

Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.