Typegpu

What it does

When your agent uses it

• Creating GPU-rendered compositions with TypeGPU
• WGSL fragment shaders
• Compute pipelines
• Liquid glass effects

Example prompts

• “/typegpu”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1Pass 1 — Downsample: render the full-res texture to a small texture (1/6 resolution). Bilinear filtering during the downsample naturally…
2. 2Pass 2 — Glass composite: sample the small texture for the frosted interior (bilinear upscale = heavy smooth blur) and the full-res…

What it can do on your machine

Read from SKILL.md and the folder at commit 645553c. 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, wgsl and html).

  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

Typegpu loads about 1.7k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 405 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~76

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

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

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 boraoztunc/skills at commit 645553c, republished under its Apache-2.0 licence (© boraoztunc). 405 words, ~1,667 tokens.

name

typegpu

description

TypeGPU and raw WebGPU adapter patterns for HyperFrames. Use when creating GPU-rendered compositions with TypeGPU, raw WebGPU, WGSL fragment shaders, compute pipelines, liquid glass effects, particle systems, or any canvas layer driven by navigator.gpu that responds to HyperFrames hf-seek events.

<canvas id="gpu-layer"></canvas>
<script>
  (async () => {
    if (!navigator.gpu) return;
    const adapter = await navigator.gpu.requestAdapter();
    if (!adapter) return;
    const device = await adapter.requestDevice();
    const canvas = document.getElementById("gpu-layer");
    canvas.width = 1920;
    canvas.height = 1080;
    const ctx = canvas.getContext("webgpu");
    const fmt = navigator.gpu.getPreferredCanvasFormat();
    ctx.configure({ device, format: fmt, alphaMode: "opaque" });

    // Build your pipeline, buffers, bind groups...
    const timeUniform = new Float32Array([0]);
    const timeBuf = device.createBuffer({
      size: 16,
      usage: GPUBufferUsage.UNIFORM | GPUBufferUsage.COPY_DST,
    });

    function render(t) {
      timeUniform[0] = t;
      device.queue.writeBuffer(timeBuf, 0, timeUniform);
      const enc = device.createCommandEncoder();
      const pass = enc.beginRenderPass({
        colorAttachments: [
          {
            view: ctx.getCurrentTexture().createView(),
            loadOp: "clear",
            clearValue: { r: 0, g: 0, b: 0, a: 1 },
            storeOp: "store",
          },
        ],
      });
      pass.setPipeline(pipeline);
      pass.setBindGroup(0, bindGroup);
      pass.draw(3);
      pass.end();
      device.queue.submit([enc.finish()]);
    }

    render(0);
    window.addEventListener("hf-seek", (e) => render(e.detail.time));
  })();
</script>

const tl = gsap.timeline({ paused: true });

// Caption tweens: synchronous, added before WebGPU init
gsap.set(".cap", { opacity: 0 });
tl.to("#cap-1", { opacity: 1, duration: 0.3 }, 1.0);
tl.to("#cap-1", { opacity: 0, duration: 0.2 }, 3.5);

window.__timelines["my-comp"] = tl;

// GPU-dependent tweens can go inside the async IIFE
(async () => {
  // ... WebGPU init ...
  const proxy = { value: 0 };
  tl.to(proxy, { value: 1, duration: 2, onUpdate: render }, 0.5);
})();

const videoEl = document.getElementById("aroll");

// Wait for video metadata before creating the texture
await new Promise((r) => {
  if (videoEl.readyState >= 1) r();
  else videoEl.addEventListener("loadedmetadata", r, { once: true });
});

// Create texture at the video's NATIVE resolution
const vw = videoEl.videoWidth,
  vh = videoEl.videoHeight;
const bgTex = device.createTexture({
  size: [vw, vh],
  format: "rgba8unorm",
  usage:
    GPUTextureUsage.COPY_DST | GPUTextureUsage.TEXTURE_BINDING | GPUTextureUsage.RENDER_ATTACHMENT,
});

function render(t) {
  try {
    device.queue.copyExternalImageToTexture({ source: videoEl }, { texture: bgTex }, [vw, vh]);
  } catch (_) {
    /* frame not decoded yet */
  }
  // ... draw ...
}

struct Vo { @builtin(position) pos: vec4f, @location(0) uv: vec2f }

@vertex fn vs(@builtin(vertex_index) vi: u32) -> Vo {
  let ps = array<vec2f, 3>(vec2f(-1., -1.), vec2f(3., -1.), vec2f(-1., 3.));
  let ts = array<vec2f, 3>(vec2f(0., 1.), vec2f(2., 1.), vec2f(0., -1.));
  return Vo(vec4f(ps[vi], 0., 1.), ts[vi]);
}

fn sdf_box(p: vec2f, half_size: vec2f, corner_radius: f32) -> f32 {
  let d = abs(p) - half_size + vec2f(corner_radius);
  return length(max(d, vec2f(0.))) + min(max(d.x, d.y), 0.) - corner_radius;
}

© boraoztunc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in typegpu of boraoztunc/skills.

Open the folder on GitHubat commit 645553c

Used in 2 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in boraoztunc/skills, which our catalogue first saw on October 7, 2026.

• alecs5am/ralphy.agents/skills/typegpuapps/desktop/resources/prompt-pack/.agents/skills/typegpu
• aiskillstore/marketplaceskills/heygen-com/typegpu