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.
ALWAYS use when creating agfxRenderTarget or agfxRenderPass objects in AGFX, or wiring up color/depth attachments, load/store ops, viewport/scissor, or draw calls within a render pass.
$ npx skills add AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AmelieHeinrich/agfx agfx-render-targets-and-passes --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/AmelieHeinrich/agfx.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agfx-render-targets-and-passes .claude/skills/agfx-render-targets-and-passes && 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 "agfx-render-targets-and-passes" agent skill from https://github.com/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passes into .claude/skills/agfx-render-targets-and-passes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agfx-render-targets-and-passes", 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/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passesType 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 AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AmelieHeinrich/agfx agfx-render-targets-and-passes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AmelieHeinrich/agfx.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/agfx-render-targets-and-passes .agents/skills/agfx-render-targets-and-passes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agfx-render-targets-and-passes" agent skill from https://github.com/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passes into .agents/skills/agfx-render-targets-and-passes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agfx-render-targets-and-passes", 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 AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AmelieHeinrich/agfx agfx-render-targets-and-passes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AmelieHeinrich/agfx.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/agfx-render-targets-and-passes .cursor/skills/agfx-render-targets-and-passes && 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 "agfx-render-targets-and-passes" agent skill from https://github.com/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passes into .cursor/skills/agfx-render-targets-and-passes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agfx-render-targets-and-passes", 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/AmelieHeinrich/agfx.git --path .claude/skills/agfx-render-targets-and-passes--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 AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AmelieHeinrich/agfx agfx-render-targets-and-passes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AmelieHeinrich/agfx.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/agfx-render-targets-and-passes .gemini/skills/agfx-render-targets-and-passes && 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 "agfx-render-targets-and-passes" agent skill from https://github.com/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passes into .gemini/skills/agfx-render-targets-and-passes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agfx-render-targets-and-passes", 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 AmelieHeinrich/agfx agfx-render-targets-and-passesInstalls 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 AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AmelieHeinrich/agfx.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/agfx-render-targets-and-passes .github/skills/agfx-render-targets-and-passes && 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 "agfx-render-targets-and-passes" agent skill from https://github.com/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passes into .github/skills/agfx-render-targets-and-passes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agfx-render-targets-and-passes", 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 AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AmelieHeinrich/agfx agfx-render-targets-and-passes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AmelieHeinrich/agfx.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/agfx-render-targets-and-passes .opencode/skills/agfx-render-targets-and-passes && 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 "agfx-render-targets-and-passes" agent skill from https://github.com/AmelieHeinrich/agfx/tree/main/.claude/skills/agfx-render-targets-and-passes into .opencode/skills/agfx-render-targets-and-passes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agfx-render-targets-and-passes", 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.
agfx-render-targets-and-passesALWAYS use when creating agfxRenderTarget or agfxRenderPass objects in AGFX, or wiring up color/depth attachments, load/store ops, viewport/scissor, or draw calls within a render pass.
Agfx Render Targets And Passes is an agent skill from AmelieHeinrich/agfx. ALWAYS use when creating agfxRenderTarget or agfxRenderPass objects in AGFX, or wiring up color/depth attachments, load/store ops, viewport/scissor, or draw calls within a render pass. Trigger for agfxRenderTargetCreate, agfxRenderPassBegin/End, agfxRenderPassAttachment, AGFXLOADOPERATION, AGFXSTOREOPERATION, agfxRenderPassSetViewport/SetScissor, agfxRenderPassDraw/DrawIndexed/DrawMesh, GBuffer/HDR/depth target setup, "wrong render target format", "render pass validation error". Do NOT trigger for swap chain…
Its SKILL.md is about 2.1k 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 licence is MIT.
Read from SKILL.md and the folder at commit d8ad38b. 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 cpp).
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.
Agfx Render Targets And Passes loads about 2.1k tokens when it runs. Until then it costs about 189 tokens; SKILL.md has 626 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 AmelieHeinrich/agfx at commit d8ad38b, republished under its MIT licence (© AmelieHeinrich). 626 words, ~2,067 tokens.
.claude/skills/agfx-render-targets-and-passes/SKILL.md (or your agent's skills folder).AGFX render targets and render passes mirror the way Metal 4, D3D12, and Vulkan dynamic rendering all express "attachment then pass", flattened behind one API. An agfxRenderTarget is a thin, cheap-to-create wrapper around a texture (or texture subresource) that tells the backend how to attach it — as a color or depth-stencil target, at a given mip/layer. An agfxRenderPass is the actual encoding scope: it groups up to 8 color attachments and one optional depth attachment, and every draw call in AGFX must happen inside one.
Render targets are intentionally lightweight: create one right before agfxRenderPassBegin and destroy it right after agfxRenderPassEnd. Don't cache them across frames — cache the underlying agfxTexture instead and re-wrap it each pass (see deferred_renderer.cpp for the GBuffer/HDR/depth targets recreated only on resize, but their agfxRenderTarget wrappers created per-pass).
Owns:
agfxRenderTargetCreateInfo / agfxRenderTargetCreate / agfxRenderTargetDestroyagfxRenderPassCreateInfo / agfxRenderPassBegin / agfxRenderPassEndagfxLoadOp / agfxStoreOp, clear colorsagfxRenderPassSetViewport, agfxRenderPassSetScissor)agfxRenderPassDraw, agfxRenderPassDrawIndexed, agfxRenderPassDrawMesh) and push constantscolorFormats[] / depthFormat in agfxRenderPipelineCreateInfo must match the pass it's used with)Doesn't own:
agfx-presentation-and-swapchainagfx-synchronizationagfxComputePass*) — those are a separate pass type for compute dispatch and copies, not covered hereagfxRenderPassExecuteIndirectBundle) and everything feeding it → agfx-mdi; the pass setup around it is ordinary and covered here, but the bundle itself, its barriers, and the supportsIndirect pipeline flag are notagfxRenderPassDrawMesh (meshShader/taskShader, the reflected group sizes) → agfx-writing-bindless-shadersRead agfx/agfx.h before writing render-target/pass code — it's the single source of truth for every struct field and enum value in this API (search for // Render target and // Render pass section markers). agfx_demo/deferred_renderer.cpp and agfx_demo/agfx_demo_main.cpp show real per-frame usage: GBuffer, SSAO, shadow map, lighting, and backbuffer passes.
agfxRenderTargetCreateInfo rtCreateInfo = {};
rtCreateInfo.texture = colorTexture; // must have AGFX_TEXTURE_USAGE_COLOR_ATTACHMENT
rtCreateInfo.format = AGFX_TEXTURE_FORMAT_UNKNOWN; // inherit the texture's own format
rtCreateInfo.mipLevel = 0;
rtCreateInfo.arrayLayer = 0;
rtCreateInfo.isDepth = false;
agfxRenderTarget* colorRT = agfxRenderTargetCreate(device, &rtCreateInfo);
// Depth target
agfxRenderTargetCreateInfo depthRtCreateInfo = {};
depthRtCreateInfo.texture = depthTexture; // must have AGFX_TEXTURE_USAGE_DEPTH_STENCIL_ATTACHMENT
depthRtCreateInfo.isDepth = true;
agfxRenderTarget* depthRT = agfxRenderTargetCreate(device, &depthRtCreateInfo);AGFX_TEXTURE_FORMAT_UNKNOWN is the correct choice whenever the render target wraps a texture whose format is already fixed (e.g. a swap chain back buffer, queried via agfxSwapChainGetFormat) — don't hardcode the format in that case, it can silently mismatch on an HDR toggle.
Every color attachment's underlying texture must already be in AGFX_RESOURCE_STATE_RENDER_TARGET, and every depth attachment's texture in AGFX_RESOURCE_STATE_DEPTH_WRITE, before calling agfxRenderPassBegin. Barrier into that state first:
agfxCommandBufferTextureBarrier(cmd, colorTexture, AGFX_RESOURCE_STATE_PIXEL_SHADER_RESOURCE, AGFX_RESOURCE_STATE_RENDER_TARGET, 0, 0, /*agglomerate=*/true);See agfx-synchronization for the agglomerate flag's semantics (ignored on D3D12/Vulkan, load-bearing on Metal) — get this wrong and you'll get correct D3D12/Vulkan output with garbage or validation errors on Metal.
agfxRenderPassCreateInfo passInfo = {};
passInfo.colorAttachmentCount = 1;
passInfo.colorAttachments[0].renderTarget = colorRT;
passInfo.colorAttachments[0].loadOp = AGFX_LOAD_OPERATION_CLEAR;
passInfo.colorAttachments[0].storeOp = AGFX_STORE_OPERATION_STORE;
passInfo.colorAttachments[0].clearColor[0] = 0.05f;
passInfo.colorAttachments[0].clearColor[1] = 0.05f;
passInfo.colorAttachments[0].clearColor[2] = 0.1f;
passInfo.colorAttachments[0].clearColor[3] = 1.0f;
passInfo.hasDepthAttachment = true;
passInfo.depthAttachment.renderTarget = depthRT;
passInfo.depthAttachment.loadOp = AGFX_LOAD_OPERATION_CLEAR;
passInfo.depthAttachment.storeOp = AGFX_STORE_OPERATION_DONT_CARE; // transient depth, not read afterwards
passInfo.width = width;
passInfo.height = height;
passInfo.name = "GBuffer";
agfxRenderPass* pass = agfxRenderPassBegin(cmd, &passInfo);
agfxRenderPassSetViewport(pass, 0, 0, (float)width, (float)height, 0.0f, 1.0f);
agfxRenderPassSetScissor(pass, 0, 0, width, height);
agfxRenderPassSetPipeline(pass, pipeline);
agfxRenderPassPushConstants(pass, &pushData, sizeof(pushData));
agfxRenderPassDrawIndexed(pass, indexBuffer, indexCount, 1, 0, 0, 0);
agfxRenderPassEnd(pass);
agfxRenderTargetDestroy(device, colorRT);
agfxRenderTargetDestroy(device, depthRT);AGFX_LOAD_OPERATION_CLEAR + AGFX_STORE_OPERATION_STORE — standard color/depth attachment that's cleared then read later (e.g. GBuffer albedo, depth used for SSAO)AGFX_LOAD_OPERATION_DONT_CARE + AGFX_STORE_OPERATION_STORE — every pixel will be fully overwritten this pass and the result is needed afterwards; skip the clear costAGFX_LOAD_OPERATION_LOAD + AGFX_STORE_OPERATION_STORE — accumulating into an attachment across multiple passes without a full clear (e.g. compositing UI on top of tonemapped output)AGFX_STORE_OPERATION_DONT_CARE — transient attachment discarded at pass end (e.g. an MSAA resolve source, or depth that's only used within the pass and never sampled afterward)agfxRenderPipelineCreateInfo::colorFormats[]/colorAttachmentCount and depthFormat must match the actual formats of the render pass's attachments the pipeline is bound in. When a pass renders to the swap chain back buffer and the app supports toggling HDR (see agfx-presentation-and-swapchain), the pipeline bound in that pass must be recreated whenever the back buffer format changes — agfx_demo_main.cpp's RecreateTonemapPipeline on the HDR toggle is the reference pattern.
A pipeline is either classic (vertexShader/fragmentShader, drawn with agfxRenderPassDraw/agfxRenderPassDrawIndexed) or mesh-shading (meshShader, optional taskShader, drawn with agfxRenderPassDrawMesh). Don't mix: calling agfxRenderPassDrawMesh with a classic pipeline bound (or vice versa) is undefined — match the draw call to how the bound pipeline was created.
© AmelieHeinrich, 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 .claude/skills/agfx-render-targets-and-passes of AmelieHeinrich/agfx.
Open the folder on GitHubat commit d8ad38b
Agfx Render Targets And Passes 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 |
|---|---|---|---|---|---|---|
| Agfx Render Targets And Passes this skillAmelieHeinrich/agfx | 146 | — | ~2.1k | 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.
AmelieHeinrich/agfx
ALWAYS use when porting an existing D3D11 engine or renderer to AGFX — translating ID3D11Device/DeviceContext/InputLayout/state-object code to agfxDevice/agfxCommandBuffer/agfxRenderPipeline calls…
AmelieHeinrich/agfx
ALWAYS use when porting an existing D3D12 engine or renderer to AGFX — translating ID3D12Device/CommandList/PipelineState/RootSignature/DescriptorHeap code to…
AmelieHeinrich/agfx
ALWAYS use when porting an existing OpenGL (or OpenGL ES) engine or renderer to AGFX — translating glGenTextures/glBindTexture/glBufferData/glUseProgram/FBO code to…
AmelieHeinrich/agfx
ALWAYS use when porting an existing Vulkan engine or renderer to AGFX — translating VkDevice/VkCommandBuffer/VkPipeline/VkDescriptorSet/VkRenderPass code to…
AmelieHeinrich/agfx
ALWAYS use when creating, resizing, or presenting through an agfxSwapChain in AGFX — window/layer handle setup, HDR toggling, vsync, resize handling, or back buffer acquire/present.
AmelieHeinrich/agfx
ALWAYS use when working with AGFX fences, frames-in-flight pacing, queue signal/wait, resource-state barriers, or the barrier "agglomerate" flag.
Categories
ALWAYS use when creating agfxRenderTarget or agfxRenderPass objects in AGFX, or wiring up color/depth attachments, load/store ops, viewport/scissor, or draw calls within a render pass. Agfx Render Targets And Passes is an agent skill from AmelieHeinrich/agfx. ALWAYS use when creating agfxRenderTarget or agfxRenderPass objects in AGFX, or wiring up color/depth attachments, load/store ops, viewport/scissor, or draw calls within a render pass.
Agfx Render Targets And Passes fits situations like: creating agfxRenderTarget; agfxRenderPass objects in AGFX; wiring up color/depth attachments; viewport/scissor.
Run `npx skills add AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a claude-code`. Or copy the skill folder (.claude/skills/agfx-render-targets-and-passes in AmelieHeinrich/agfx) into .claude/skills/agfx-render-targets-and-passes in your project. Claude Code loads it when a task matches its description.
Run `npx skills add AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a codex`. Or copy the skill folder (.claude/skills/agfx-render-targets-and-passes in AmelieHeinrich/agfx) into .agents/skills/agfx-render-targets-and-passes 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 AmelieHeinrich/agfx --skill agfx-render-targets-and-passes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agfx-render-targets-and-passes, .gemini/skills/agfx-render-targets-and-passes, .github/skills/agfx-render-targets-and-passes and .opencode/skills/agfx-render-targets-and-passes in your project.
SKILL.md names no scripts, command-line tools or credentials: Agfx Render Targets And Passes 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.
Agfx Render Targets And Passes is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.3k 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 Agfx Render Targets And Passes: 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.
AmelieHeinrich (a GitHub user) maintains it in AmelieHeinrich/agfx, which has 146 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 27, 2026.
Source: AmelieHeinrich/agfx on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.