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.
A skill your agent uses when creating Sprites or Images in Phaser 4.
$ npx skills add autonomous-ai/openharness --skill sprites-and-images -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness sprites-and-images --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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/sprites-and-images .claude/skills/sprites-and-images && rm -rf skills-srcUse ~/.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/
Install the "sprites-and-images" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-images into .claude/skills/sprites-and-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sprites-and-images", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-imagesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autonomous-ai/openharness --skill sprites-and-images -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness sprites-and-images --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/phaser/skills/sprites-and-images .agents/skills/sprites-and-images && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sprites-and-images" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-images into .agents/skills/sprites-and-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sprites-and-images", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill sprites-and-images -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness sprites-and-images --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/phaser/skills/sprites-and-images .cursor/skills/sprites-and-images && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sprites-and-images" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-images into .cursor/skills/sprites-and-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sprites-and-images", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/phaser/skills/sprites-and-images--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autonomous-ai/openharness --skill sprites-and-images -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness sprites-and-images --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/phaser/skills/sprites-and-images .gemini/skills/sprites-and-images && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sprites-and-images" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-images into .gemini/skills/sprites-and-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sprites-and-images", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autonomous-ai/openharness sprites-and-imagesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autonomous-ai/openharness --skill sprites-and-images -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/phaser/skills/sprites-and-images .github/skills/sprites-and-images && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sprites-and-images" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-images into .github/skills/sprites-and-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sprites-and-images", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill sprites-and-images -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness sprites-and-images --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/phaser/skills/sprites-and-images .opencode/skills/sprites-and-images && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sprites-and-images" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/sprites-and-images into .opencode/skills/sprites-and-images/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sprites-and-images", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
sprites-and-imagesA skill your agent uses when creating Sprites or Images in Phaser 4.
Sprites And Images is an agent skill from autonomous-ai/openharness. Use this skill when creating Sprites or Images in Phaser 4. Covers factory methods, texture/frame selection, position, scale, rotation, tint, flip, alpha, origin, depth, and the component mixin system. Triggers on: Sprite, Image, this.add.sprite, this.add.image, texture, setTint, setAlpha.
Its SKILL.md is about 3.7k 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.
Read from SKILL.md and the folder at commit cc4983e. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Sprites And Images loads about 3.7k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 773 words of instructions outside code blocks.
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.
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.
The full file from autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 773 words, ~3,736 tokens.
.claude/skills/sprites-and-images/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Creating and manipulating Sprite and Image game objects in Phaser 4 -- factory methods, texture/frame selection, the component mixin system, and common visual operations (position, scale, rotation, tint, flip, alpha, origin, depth).
Key source paths: src/gameobjects/sprite/, src/gameobjects/image/, src/gameobjects/GameObject.js, src/gameobjects/components/
Related skills: ../loading-assets/SKILL.md, ../animations/SKILL.md, ../physics-arcade/SKILL.md, ../game-object-components/SKILL.md
// In a Scene's create() method:
// Static image (no animation support, slightly cheaper)
const bg = this.add.image(400, 300, 'background');
// Sprite (supports animations)
const player = this.add.sprite(100, 200, 'player', 'idle-0');
// Common operations -- all methods return `this` for chaining
player.setPosition(200, 300);
player.setScale(2);
player.setAngle(45);
player.setTint(0xff0000);
player.setAlpha(0.8);
player.setOrigin(0, 1); // bottom-left
player.setDepth(10);
player.setFlip(true, false); // flip horizontally
player.setVisible(false);
// Chained
this.add.sprite(100, 100, 'coin')
.setScale(0.5)
.setTint(0xffff00)
.play('spin');Both extend GameObject and share the same set of component mixins. The only difference is that Sprite includes an AnimationState instance (sprite.anims) and animation convenience methods (play, stop, chain, etc.).
| Feature | Image | Sprite |
|---|---|---|
| Static texture display | Yes | Yes |
| Tint, alpha, flip, scale, rotate | Yes | Yes |
| Physics body | Yes | Yes |
| Input / hit area | Yes | Yes |
Animation (play, stop, chain) | No | Yes |
preUpdate called each frame | No | Yes (updates animation) |
Added to Scene updateList | No | Yes |
Rule of thumb: Use Image for anything that does not need frame-by-frame animation. It skips the per-frame preUpdate cost and has a smaller API surface. Use Sprite only when you need the Animation component.
Phaser builds Game Object classes by mixing component objects into the prototype. Both Sprite and Image share this identical Mixins array (sourced from src/gameobjects/sprite/Sprite.js and src/gameobjects/image/Image.js):
Mixins: [
Components.Alpha,
Components.BlendMode,
Components.Depth,
Components.Flip,
Components.GetBounds,
Components.Lighting,
Components.Mask,
Components.Origin,
Components.RenderNodes,
Components.ScrollFactor,
Components.Size,
Components.TextureCrop,
Components.Tint,
Components.Transform,
Components.Visible,
SpriteRender / ImageRender // render-specific (differs per class)
]The base GameObject class itself mixes in:
Mixins: [
Components.Filters,
Components.RenderSteps
]Each component adds specific properties and methods to every instance. For example, Components.Transform adds x, y, scale, rotation, setPosition(), etc. The full list of available components is in src/gameobjects/components/index.js.
Key point for agents: When you see a method like setAlpha() on a Sprite, it comes from Components.Alpha, not from the Sprite class itself. The component source file is the authoritative reference for that method's signature and behavior.
Both Sprite and Image use the TextureCrop component which provides:
texture -- the Phaser.Textures.Texture instanceframe -- the current Phaser.Textures.Frame instancesetTexture(key, frame) -- change the texture (and optionally the frame)setFrame(frame, updateSize, updateOrigin) -- change only the framesetCrop(x, y, width, height) -- crop a rectangular region of the textureisCropped -- boolean, toggle cropping on/off after setCropThe texture parameter in factory methods and constructors accepts either a string key (as registered in the Texture Manager) or a Phaser.Textures.Texture instance.
The frame parameter accepts a string name or numeric index into the texture's frame collection. If omitted, the base frame (frame 0 / '__BASE') is used.
// Change texture at runtime
sprite.setTexture('enemies', 'goblin-walk-1');
// Change only the frame (must belong to current texture)
sprite.setFrame('goblin-walk-2');
// setFrame signature:
// setFrame(frame, updateSize=true, updateOrigin=true)
// Pass false to prevent automatic resize/origin recalculation
sprite.setFrame('small-frame', false, false);
// Crop to show only a 50x50 region starting at (10, 10)
sprite.setCrop(10, 10, 50, 50);
// Reset crop
sprite.setCrop();Transform component (src/gameobjects/components/Transform.js):
// Properties (all read/write)
sprite.x // horizontal position (default: 0)
sprite.y // vertical position (default: 0)
sprite.z // z position (does NOT control render order -- use depth)
sprite.w // w position
// Methods
sprite.setPosition(x, y, z, w) // y defaults to x if omitted
sprite.setRandomPosition(x, y, w, h) // random within area; defaults to game size
sprite.copyPosition(source) // copy from any {x, y} objectSize component (src/gameobjects/components/Size.js):
sprite.width // native (un-scaled) width
sprite.height // native (un-scaled) height
sprite.displayWidth // scaled width (read/write -- setting adjusts scaleX)
sprite.displayHeight // scaled height (read/write -- setting adjusts scaleY)
sprite.setSize(width, height) // set internal size (not visual)
sprite.setDisplaySize(width, height) // set visual size (adjusts scale)
sprite.setSizeToFrame(frame) // reset size to match frameTransform component (continued):
// Scale properties
sprite.scale // uniform scale (getter returns average of scaleX+scaleY)
sprite.scaleX // horizontal scale (default: 1)
sprite.scaleY // vertical scale (default: 1)
// Scale methods
sprite.setScale(x, y) // y defaults to x if omitted
// Rotation properties
sprite.rotation // in radians (right-hand clockwise: 0=right, PI/2=down)
sprite.angle // in degrees (0=right, 90=down, 180/-180=left, -90=up)
// Rotation methods
sprite.setRotation(radians) // defaults to 0
sprite.setAngle(degrees) // defaults to 0Tint component (src/gameobjects/components/Tint.js) -- WebGL only:
// Properties
sprite.tint // overall tint (getter returns tintTopLeft)
sprite.tintTopLeft // default: 0xffffff
sprite.tintTopRight // default: 0xffffff
sprite.tintBottomLeft // default: 0xffffff
sprite.tintBottomRight // default: 0xffffff
sprite.tintMode // default: Phaser.TintModes.MULTIPLY
sprite.isTinted // read-only boolean
// Methods
sprite.setTint(topLeft, topRight, bottomLeft, bottomRight)
// If only topLeft given, applies uniformly to all four corners
sprite.setTintMode(mode) // Phaser.TintModes.MULTIPLY | FILL | ADD | SCREEN | OVERLAY | HARD_LIGHT
sprite.clearTint() // resets to 0xffffff + MULTIPLY modePhaser 4 change: setTintFill() is removed. Use setTint(color).setTintMode(Phaser.TintModes.FILL) instead.
Alpha component (src/gameobjects/components/Alpha.js):
// Properties
sprite.alpha // global alpha 0-1 (default: 1)
sprite.alphaTopLeft // per-corner alpha (WebGL only)
sprite.alphaTopRight
sprite.alphaBottomLeft
sprite.alphaBottomRight
// Methods
sprite.setAlpha(topLeft, topRight, bottomLeft, bottomRight)
// If only topLeft given, applies uniformly to whole object
sprite.clearAlpha() // resets to 1 (fully opaque)Setting alpha to 0 clears the render flag so the object is not drawn. Setting it back to any non-zero value restores it.
Flip component (src/gameobjects/components/Flip.js):
// Properties
sprite.flipX // boolean (default: false)
sprite.flipY // boolean (default: false)
// Methods
sprite.setFlipX(value) // set horizontal flip
sprite.setFlipY(value) // set vertical flip
sprite.setFlip(x, y) // set both at once
sprite.toggleFlipX() // invert current horizontal flip
sprite.toggleFlipY() // invert current vertical flip
sprite.resetFlip() // set both to falseFlipping is a rendering toggle only. It does not affect physics bodies or hit areas. Flip occurs from the middle of the texture and does not change the scale value.
Origin component (src/gameobjects/components/Origin.js):
// Properties (normalized 0-1)
sprite.originX // default: 0.5 (center)
sprite.originY // default: 0.5 (center)
sprite.displayOriginX // pixel value (originX * width)
sprite.displayOriginY // pixel value (originY * height)
// Methods
sprite.setOrigin(x, y) // y defaults to x; defaults to 0.5
sprite.setDisplayOrigin(x, y) // set origin in pixels; y defaults to x
sprite.setOriginFromFrame() // use Frame pivot if set, else 0.5
sprite.updateDisplayOrigin() // recalculate pixel origin from normalizedDepth component (src/gameobjects/components/Depth.js):
// Properties
sprite.depth // default: 0 (higher = renders on top)
// Methods
sprite.setDepth(value)
sprite.setToTop() // move to top of display list (no depth change)
sprite.setToBack() // move to back of display list (no depth change)
sprite.setAbove(gameObject) // position above another object in the list
sprite.setBelow(gameObject) // position below another object in the listSetting depth queues a depth sort in the Scene. The setToTop/setToBack/setAbove/setBelow methods change display list position without modifying the depth value.
sprite.destroy(); // removes from display list, update list, and cleans up
sprite.ignoreDestroy = true; // prevent destruction (you manage lifecycle manually)
sprite.isDestroyed // boolean, true after destroy() has been calledFor Sprites, destroy() also calls this.anims.destroy() to clean up the AnimationState.
Visible (src/gameobjects/components/Visible.js):
sprite.visible // boolean (default: true)
sprite.setVisible(value) // invisible objects skip rendering but still updateScrollFactor (src/gameobjects/components/ScrollFactor.js):
sprite.scrollFactorX // default: 1 (moves with camera)
sprite.scrollFactorY // default: 1
sprite.setScrollFactor(x, y) // 0 = fixed to camera; y defaults to xBlendMode (src/gameobjects/components/BlendMode.js):
sprite.blendMode // default: Phaser.BlendModes.NORMAL
sprite.setBlendMode(value) // Phaser.BlendModes.ADD, MULTIPLY, SCREEN, ERASE, etc.Performance note: Changing blend mode breaks WebGL batches. Group objects by blend mode when possible (e.g., render all ADD-mode sprites together) to minimize draw calls.
Source: src/gameobjects/sprite/SpriteFactory.js
// Signature
this.add.sprite(x, y, texture, frame);| Param | Type | Required | Description |
|---|---|---|---|
x | number | Yes | Horizontal position in world coordinates |
y | number | Yes | Vertical position in world coordinates |
texture | string | Phaser.Textures.Texture | Yes | Texture key or Texture instance |
frame | string | number | No | Frame name or index within the texture |
Returns: Phaser.GameObjects.Sprite
Internally does: this.displayList.add(new Sprite(this.scene, x, y, texture, frame))
The Sprite constructor calls: setTexture -> setPosition -> setSizeToFrame -> setOriginFromFrame -> initRenderNodes.
Source: src/gameobjects/image/ImageFactory.js
// Signature
this.add.image(x, y, texture, frame);| Param | Type | Required | Description |
|---|---|---|---|
x | number | Yes | Horizontal position in world coordinates |
y | number | Yes | Vertical position in world coordinates |
texture | string | Phaser.Textures.Texture | Yes | Texture key or Texture instance |
frame | string | number | No | Frame name or index within the texture |
Returns: Phaser.GameObjects.Image
Internally does: this.displayList.add(new Image(this.scene, x, y, texture, frame))
The Image constructor calls the same init sequence as Sprite: setTexture -> setPosition -> setSizeToFrame -> setOriginFromFrame -> initRenderNodes.
Scalable UI panels with fixed-size corners and stretchable edges/center. Ideal for buttons, panels, and dialog boxes that need to resize without distorting borders.
// nineslice(x, y, texture, frame, width, height, leftWidth, rightWidth, topHeight, bottomHeight)
const panel = this.add.nineslice(400, 300, 'panel', null, 300, 200, 20, 20, 20, 20);
// Resize at runtime -- corners stay fixed, edges stretch
panel.setSize(500, 400);Repeating texture that fills an area. Supports atlas frames in v4 and a new tileRotation property.
const bg = this.add.tileSprite(400, 300, 800, 600, 'grass');
// Scroll the tile in update() for parallax backgrounds
bg.tilePositionX += 0.5;
bg.tilePositionY += 0.25;
// v4: rotate the tile pattern
bg.tileRotation = 0.1;High-performance batched rendering for large numbers of static or semi-static sprites. Blitter children (Bobs) have no rotation, scale, or physics, but render significantly faster than individual Sprites.
const blitter = this.add.blitter(0, 0, 'particles');
// Create Bobs (lightweight display objects)
for (let i = 0; i < 1000; i++) {
const bob = blitter.create(
Phaser.Math.Between(0, 800),
Phaser.Math.Between(0, 600),
'particle_01' // frame name within the texture
);
bob.setAlpha(Math.random());
}Video playback as a game object with position, scale, and filter support.
// Load in preload:
this.load.video('intro', 'intro.mp4');
// Create in create:
const video = this.add.video(400, 300, 'intro');
video.play();For detailed configuration options, API reference tables, and source file maps, see the reference guide.
© 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
SKILL.md and 1 other file (references) in store/agents/phaser/skills/sprites-and-images of autonomous-ai/openharness.
Open the folder on GitHubat commit cc4983e
Sprites And Images 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sprites And Images this skillautonomous-ai/openharness | 1.2k | — | ~3.7k | Automated safety check: Pass | MIT | |
| Image to Three.js Modelimg2threejs/img2threejs | 18k | 1 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Web CloneJane-xiaoer/claude-skill-web-clone | 1k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Threejs Game Directormajidmanzarpour/threejs-game-skills | 2.5k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Game Asset Generatorhtdt/godogen | 7.1k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Threejs Gameplay Systemsvalkor-ai/loom | 1.2k | 1 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 |
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.
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 /…
majidmanzarpour/threejs-game-skills
Entrypoint for building, upgrading, and finishing Three.js browser games.
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
valkor-ai/loom
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…
CyberAgentGameEntertainment/NovaShader
Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.
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.
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.
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
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.
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.
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Categories
A skill your agent uses when creating Sprites or Images in Phaser 4. Sprites And Images is an agent skill from autonomous-ai/openharness. Use this skill when creating Sprites or Images in Phaser 4.
Sprites And Images fits situations like: creating Sprites; images in Phaser 4; this.add.sprite.
Run `npx skills add autonomous-ai/openharness --skill sprites-and-images -a claude-code`. Or copy the skill folder (store/agents/phaser/skills/sprites-and-images in autonomous-ai/openharness) into .claude/skills/sprites-and-images in your project. Claude Code loads it when a task matches its description.
Run `npx skills add autonomous-ai/openharness --skill sprites-and-images -a codex`. Or copy the skill folder (store/agents/phaser/skills/sprites-and-images in autonomous-ai/openharness) into .agents/skills/sprites-and-images in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill sprites-and-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sprites-and-images, .gemini/skills/sprites-and-images, .github/skills/sprites-and-images and .opencode/skills/sprites-and-images in your project.
SKILL.md names no scripts, command-line tools or credentials: Sprites And Images is instructions for the agent only.
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.
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.
Sprites And Images is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.7k tokens (SKILL.md is roughly 15k 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 2.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Sprites And Images: 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, 2.5k 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.
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 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.