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 using RenderTexture or DynamicTexture in Phaser 4.
$ npx skills add autonomous-ai/openharness --skill render-textures -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness render-textures --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/render-textures .claude/skills/render-textures && 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 "render-textures" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/render-textures into .claude/skills/render-textures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "render-textures", 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/render-texturesType 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 render-textures -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness render-textures --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/render-textures .agents/skills/render-textures && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "render-textures" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/render-textures into .agents/skills/render-textures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "render-textures", 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 render-textures -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness render-textures --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/render-textures .cursor/skills/render-textures && 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 "render-textures" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/render-textures into .cursor/skills/render-textures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "render-textures", 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/render-textures--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 render-textures -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness render-textures --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/render-textures .gemini/skills/render-textures && 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 "render-textures" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/render-textures into .gemini/skills/render-textures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "render-textures", 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 render-texturesInstalls 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 render-textures -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/render-textures .github/skills/render-textures && 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 "render-textures" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/render-textures into .github/skills/render-textures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "render-textures", 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 render-textures -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 render-textures --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/render-textures .opencode/skills/render-textures && 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 "render-textures" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/phaser/skills/render-textures into .opencode/skills/render-textures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "render-textures", 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.
render-texturesA skill your agent uses when using RenderTexture or DynamicTexture in Phaser 4.
Render Textures is an agent skill from autonomous-ai/openharness. Use this skill when using RenderTexture or DynamicTexture in Phaser 4. Covers drawing game objects to textures, dynamic texture creation, snapshot/screenshot, stamps, and off-screen rendering. Triggers on: RenderTexture, DynamicTexture, snapshot, draw to texture, stamp.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
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.
12 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 54a1f1b. 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.
Render Textures loads about 4.3k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 1,341 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 54a1f1b, republished under its MIT licence (© autonomous-ai). 1,341 words, ~4,317 tokens.
.claude/skills/render-textures/SKILL.md (or your agent's skills folder).Drawing game objects to off-screen textures in Phaser 4 -- RenderTexture game object, DynamicTexture for shared textures, the Stamp helper, command-buffer rendering, snapshots, procedural generation, and minimap patterns.
Key source paths: src/gameobjects/rendertexture/, src/textures/DynamicTexture.js, src/gameobjects/stamp/, src/textures/typedefs/StampConfig.js, src/textures/typedefs/CaptureConfig.js
Related skills: ../sprites-and-images/SKILL.md, ../loading-assets/SKILL.md, ../cameras/SKILL.md
// In a Scene's create() method:
// 1. RenderTexture -- a visible game object with its own DynamicTexture
const rt = this.add.renderTexture(400, 300, 256, 256);
rt.draw('player', 128, 128); // draw a texture by key at center
rt.fill(0x222244, 0.5); // semi-transparent fill
rt.render(); // flush the command buffer
// 2. DynamicTexture -- a shared texture in the Texture Manager
const dt = this.textures.addDynamicTexture('composite', 512, 512);
dt.stamp('coin', null, 64, 64, { scale: 2, angle: 45 });
dt.render();
this.add.image(400, 300, 'composite'); // any game object can use it
// 3. Stamp game object -- lightweight Image that ignores camera scroll
const hud = this.add.stamp(10, 10, 'heart');Phaser 4 splits texture-drawing into two layers:
| RenderTexture | DynamicTexture | |
|---|---|---|
| What it is | Image game object + auto-created DynamicTexture | Texture in the Texture Manager |
| Created via | this.add.renderTexture(x, y, w, h) | this.textures.addDynamicTexture(key, w, h) |
| Visible on its own | Yes (it extends Image) | No (must be assigned to a game object) |
| Shared across objects | Possible via saveTexture(key) | Yes, by key |
| Cross-scene use | No (belongs to one Scene) | Yes (textures are global) |
| Has position/scale/alpha | Yes (all Image components) | No (it is a Texture, not a GameObject) |
When to use which:
RenderTexture is a thin proxy. Methods like draw(), stamp(), fill(), clear(), erase(), snapshot() all delegate to its underlying this.texture (a DynamicTexture).
Origin note: RenderTexture extends Image, so its origin defaults to (0.5, 0.5). If you want top-left positioning (common for full-screen or minimap RTs), call rt.setOrigin(0, 0).
In Phaser 4, drawing calls (draw, stamp, fill, clear, erase, repeat, capture) do not execute immediately. They push commands into a commandBuffer array. You must call .render() to flush and execute the buffer.
rt.clear();
rt.fill(0x000000);
rt.draw(sprite, 128, 128);
rt.render(); // REQUIRED -- nothing appears without thisFor RenderTexture game objects, the renderMode property controls automatic rendering:
| Mode | Behavior |
|---|---|
'render' (default) | Draws the texture contents to the frame each tick. You call render() manually when content changes. |
'redraw' | Calls render() automatically every frame but does NOT display itself. Useful for textures reused by other objects. |
'all' | Calls render() every frame AND draws itself to the frame. |
rt.setRenderMode('all'); // auto-render + display every frame
rt.setRenderMode('all', true); // same, plus preserve the command bufferBy default the command buffer clears after render(). Call preserve(true) to keep commands between renders, so the same drawing replays each frame:
rt.preserve(true);
rt.clear();
rt.draw(sprite);
// On every subsequent render(), clear + draw will repeatStamp (this.add.stamp(x, y, texture, frame)) is a lightweight Image subclass that ignores camera scroll and transform during rendering. It is used internally by DynamicTexture for drawing operations and is also useful for HUD elements. It extends Image with custom render nodes (DefaultStampNodes).
stamp() Method vs the Stamp Game ObjectThese are different things:
rt.stamp(key, frame, x, y, config) -- a method on RenderTexture/DynamicTexture that draws a texture frame to the surface with transform options (alpha, tint, angle, scale, origin, blendMode).this.add.stamp(x, y, texture, frame) -- a factory that creates a Stamp game object added to the Scene display list.const rt = this.add.renderTexture(0, 0, 800, 600);
// Single game object at an offset
rt.draw(sprite, 100, 100);
// Array of objects
rt.draw([sprite1, sprite2, sprite3]);
// Group or Container (only visible children are drawn)
rt.draw(enemyGroup);
rt.draw(myContainer, 50, 50); // offset added to children positions
// Entire Scene display list
rt.draw(this.children);
// Texture by string key
rt.draw('explosion', 200, 200);
// Don't forget to flush
rt.render();The draw() method accepts: renderable game objects, Groups, Containers, Display Lists, other RenderTextures/DynamicTextures, Texture Frames, texture key strings, or arrays of any of these.
Note: alpha and tint parameters on draw() only apply to Texture Frames/strings. Game objects use their own alpha and tint when drawn.
The stamp() method draws a texture frame with full transform control. The frame is centered on the x/y position by default (origin 0.5).
rt.stamp('bullet', null, 100, 100, {
alpha: 0.8,
tint: 0xff0000,
angle: 45, // degrees (takes precedence over rotation)
scale: 2, // uniform scale
scaleX: 1.5, // overrides scale for X
scaleY: 0.5, // overrides scale for Y
originX: 0, // top-left origin
originY: 0,
blendMode: 0
});
rt.render();The capture() method draws a game object with temporary property overrides, restoring originals afterward:
rt.capture(player, {
x: 64,
y: 64,
scale: 0.5,
alpha: 0.8,
rotation: Math.PI / 4,
transform: 'world', // 'local', 'world', or a TransformMatrix
camera: someCamera // optional camera override
});
rt.render();This is useful for drawing an object at a different position/scale without modifying the object itself.
// Fill entire texture with color
rt.fill(0xff0000); // solid red
rt.fill(0x000000, 0.5); // semi-transparent black
// Fill a region
rt.fill(0x00ff00, 1, 10, 10, 100, 50); // green rect at (10,10) size 100x50
// Clear everything (transparent)
rt.clear();
// Clear a region
rt.clear(10, 10, 100, 50);
rt.render();Erase uses ERASE blend mode to cut holes in the texture:
rt.fill(0xffffff); // white background
rt.erase(circleSprite, 100, 100); // punch a hole shaped like the sprite
rt.render();// Fill the entire RenderTexture with a tiled pattern
rt.repeat('grass', null); // tile the whole surface
rt.repeat('brick', null, 0, 0, 256, 128); // tile a specific region
rt.repeat('tile', 'frame2', 0, 0, 512, 512, {
tileScaleX: 2,
tileScaleY: 2,
tilePositionX: 16,
alpha: 0.8
});
rt.render();Snapshots read pixel data from the framebuffer. They are expensive and blocking -- use sparingly.
// Full texture snapshot -- callback receives an HTMLImageElement
rt.snapshot(function (image) {
document.body.appendChild(image); // or use as texture source
});
// Area snapshot
rt.snapshotArea(0, 0, 128, 128, function (image) {
// image is 128x128 region from top-left
}, 'image/jpeg', 0.8);
// Single pixel -- callback receives a Phaser.Display.Color
rt.snapshotPixel(64, 64, function (color) {
console.log(color.r, color.g, color.b, color.a);
});const rt = this.add.renderTexture(0, 0, 256, 256);
rt.draw(complexScene);
rt.render();
// Register in the Texture Manager under a key
rt.saveTexture('composited');
// Now any game object can use it
this.add.image(400, 300, 'composited');
this.add.sprite(100, 100, 'composited');
// Updates to the RenderTexture automatically reflect on all usersFor DynamicTexture, the key is set at creation time:
const dt = this.textures.addDynamicTexture('terrain', 1024, 1024);
dt.repeat('grass', null);
dt.render();
this.add.image(512, 512, 'terrain'); // already keyedconst dt = this.textures.addDynamicTexture('starfield', 800, 600);
dt.fill(0x000011);
for (let i = 0; i < 200; i++) {
const x = Phaser.Math.Between(0, 800);
const y = Phaser.Math.Between(0, 600);
const brightness = Phaser.Math.FloatBetween(0.3, 1);
dt.stamp('star', null, x, y, { alpha: brightness, scale: Phaser.Math.FloatBetween(0.5, 1.5) });
}
dt.render();
this.add.image(400, 300, 'starfield');create() {
// Small RenderTexture as minimap
this.minimap = this.add.renderTexture(700, 50, 150, 100);
this.minimap.setScrollFactor(0); // fixed to camera
this.minimap.setRenderMode('all'); // auto-render every frame
this.minimap.preserve(true);
}
// In update or a callback:
this.minimap.clear();
this.minimap.fill(0x111111);
// Draw scaled-down versions of world objects
this.minimap.capture(player, { x: px * 0.1, y: py * 0.1, scale: 0.1 });
// render() is automatic in 'all' modeInsert logic between draw commands that executes during render():
rt.clear();
rt.draw(background);
rt.callback(() => {
// Runs during render, after background is drawn
sprite.setTint(0xff0000);
});
rt.draw(sprite);
rt.callback(() => {
sprite.setTint(0xffffff); // restore after drawing
});
rt.render();// Resize erases all content and recreates the framebuffer
rt.resize(512, 512);
// Optional: disable force-even rounding
rt.resize(513, 513, false);Both RenderTexture and DynamicTexture have a .camera property that controls how game objects are positioned when drawn. Scroll, zoom, and rotate this camera to transform drawn content. Note: stamp() ignores the camera; only draw() and game object rendering respect it.
rt.camera.setScroll(100, 50);
rt.camera.setZoom(2);
rt.draw(sprite); // sprite drawn with camera transform applied
rt.render();| Method | Signature | Description |
|---|---|---|
draw | (entries, x?, y?, alpha?, tint?) | Draw game objects, textures, groups, etc. |
capture | (entry, config) | Draw with temporary property overrides |
stamp | (key, frame?, x?, y?, config?) | Stamp a texture frame with transform |
erase | (entries, x?, y?) | Draw using ERASE blend mode |
fill | (rgb, alpha?, x?, y?, w?, h?) | Fill with color |
clear | (x?, y?, w?, h?) | Clear to transparent |
repeat | (key, frame?, x?, y?, w?, h?, config?) | Tile a texture as fill pattern |
render | () | Flush the command buffer |
preserve | (bool) | Keep command buffer between renders |
callback | (fn) | Insert callback into command buffer |
resize | (w, h?, forceEven?) | Resize (erases content) |
saveTexture | (key) | Register in Texture Manager |
setRenderMode | (mode, preserve?) | Set 'render', 'redraw', or 'all' |
snapshot | (callback, type?, quality?) | Full snapshot to Image |
snapshotArea | (x, y, w, h, callback, type?, quality?) | Area snapshot |
snapshotPixel | (x, y, callback) | Single pixel to Color |
Same drawing methods as RenderTexture (draw, stamp, erase, fill, clear, repeat, capture, render, preserve, callback, snapshot, snapshotArea, snapshotPixel), plus:
| Method/Property | Description |
|---|---|
setSize(w, h?, forceEven?) | Resize the texture |
camera | Internal Camera for draw positioning |
commandBuffer | Array of pending draw commands |
drawingContext | WebGL DrawingContext with framebuffer |
getWebGLTexture() | Returns the underlying WebGLTextureWrapper |
stamp() config parameter)| Property | Default | Description |
|---|---|---|
alpha | 1 | Alpha value |
tint | 0xffffff | Tint color (WebGL only) |
angle | 0 | Degrees (overrides rotation if non-zero) |
rotation | 0 | Radians |
scale | 1 | Uniform scale |
scaleX / scaleY | 1 | Per-axis scale (overrides scale) |
originX / originY | 0.5 | Origin point |
blendMode | 0 | Blend mode |
capture() config parameter)| Property | Description |
|---|---|
transform | 'local', 'world', or a TransformMatrix |
camera | Camera override for rendering |
x, y, alpha, tint, angle, rotation | Override game object properties temporarily |
scale, scaleX, scaleY | Scale overrides |
originX, originY, blendMode | Additional overrides |
this.add.renderTexture(x, y, width?, height?) // default 32x32
this.add.stamp(x, y, texture, frame?)
this.textures.addDynamicTexture(key, width?, height?, forceEven?) // default 256x256Must call render(). In Phaser 4, drawing methods buffer commands. Nothing appears until render() is called (unless using renderMode: 'all' or 'redraw').
Cannot draw to itself. A DynamicTexture/RenderTexture silently skips entries that reference itself.
Command buffer clears after render. Call preserve(true) before drawing if you need the same commands to replay each frame.
stamp() ignores the internal camera. Only game objects drawn via draw() or capture() respect the .camera property. Texture stamps are positioned absolutely.
Default sizes differ. RenderTexture defaults to 32x32. DynamicTexture defaults to 256x256.
forceEven rounds dimensions up. By default, width/height are rounded to even numbers for rendering quality. Pass false as the last argument if you need exact odd dimensions.
Snapshots are expensive. They use readPixels (WebGL) which blocks the GPU pipeline. Avoid per-frame snapshots. snapshotPixel is cheaper than full snapshot.
WebGL1 has no anti-aliasing on framebuffers. Shapes and Graphics drawn to a RenderTexture may have jagged edges. Use pre-rendered sprite textures instead.
resize() erases content. Resizing destroys and recreates the framebuffer.
saveTexture renames, does not copy. Calling saveTexture(key) assigns the DynamicTexture to the Texture Manager under that key. Calling it again with a different key renames it. Destroying the RenderTexture without saving first destroys the texture.
draw() alpha/tint params only affect Texture Frames. When drawing game objects, they use their own alpha and tint values. The alpha and tint parameters on draw() only apply when drawing texture strings or Frame instances.
WebGL context loss. DynamicTexture contents are lost on context loss. Listen for the restorewebgl event to redraw.
Groups/Containers: x, y offset is additive. When drawing a Group or Container with rt.draw(group, x, y), the x/y offset is added to each child's position. Children at (100, 50) drawn with offset (10, 10) appear at (110, 60) in the texture.
| File | Description |
|---|---|
src/gameobjects/rendertexture/RenderTexture.js | RenderTexture game object (extends Image, proxies to DynamicTexture) |
src/gameobjects/rendertexture/RenderTextureFactory.js | this.add.renderTexture() factory registration |
src/gameobjects/rendertexture/RenderTextureRender.js | WebGL/Canvas render functions for RenderTexture |
src/gameobjects/rendertexture/RenderTextureRenderModes.js | Enum: RENDER, REDRAW, ALL |
src/textures/DynamicTexture.js | Core DynamicTexture class (command buffer, drawing, snapshots) |
src/textures/DynamicTextureCommands.js | Command constants (CLEAR, FILL, STAMP, DRAW, ERASE, etc.) |
src/textures/typedefs/StampConfig.js | StampConfig typedef for stamp() |
src/textures/typedefs/CaptureConfig.js | CaptureConfig typedef for capture() |
src/gameobjects/stamp/Stamp.js | Stamp game object (light Image, ignores camera scroll) |
src/gameobjects/stamp/StampFactory.js | this.add.stamp() factory registration |
© 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
Just SKILL.md in store/agents/phaser/skills/render-textures of autonomous-ai/openharness.
Open the folder on GitHubat commit 54a1f1b
Render Textures 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 |
|---|---|---|---|---|---|---|
| Render Textures this skillautonomous-ai/openharness | 1.1k | — | ~4.3k | 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 | 2.4k | — | ~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 using RenderTexture or DynamicTexture in Phaser 4. Render Textures is an agent skill from autonomous-ai/openharness. Use this skill when using RenderTexture or DynamicTexture in Phaser 4.
Render Textures fits situations like: using RenderTexture; dynamicTexture in Phaser 4; : RenderTexture; draw to texture.
Run `npx skills add autonomous-ai/openharness --skill render-textures -a claude-code`. Or copy the skill folder (store/agents/phaser/skills/render-textures in autonomous-ai/openharness) into .claude/skills/render-textures in your project. Claude Code loads it when a task matches its description.
Run `npx skills add autonomous-ai/openharness --skill render-textures -a codex`. Or copy the skill folder (store/agents/phaser/skills/render-textures in autonomous-ai/openharness) into .agents/skills/render-textures 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 render-textures -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/render-textures, .gemini/skills/render-textures, .github/skills/render-textures and .opencode/skills/render-textures in your project.
SKILL.md names no scripts, command-line tools or credentials: Render Textures 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.
Render Textures is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Render Textures: 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.
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.