vgpu — Claude Code skill: what it does, how to install
Guides agents through building WebGPU projects with vgpu, relying on local bundled docs, WGSL workflows, and Blender asset pipelines.
npx skills add vercel-labs/vgpu --skill vgpu -a claude-codeWhat vgpu does
The skill instructs coding assistants how to handle WebGPU applications using vgpu, @vgpu packages, and its CLI. It covers WGSL shaders, rendering in browsers or Node, performance profiling, and 3D scene assembly with cameras, transforms, and physics. For assets, it outlines Blender modeling, normal and ambient occlusion baking, LOD setups, and runtime validation.
The skill strictly enforces version neutrality. Instead of relying on model memory or remote docs, the agent queries the project-local CLI using commands such as pnpm exec vgpu docs cat or npm exec --no -- vgpu docs find. This keeps API usage tied to the exact installed package.
Bare npx vgpu or bunx vgpu commands are prohibited for version discovery because package managers may silently download unpinned releases. If the binary is missing, dependencies must be restored or inspected via lockfiles rather than defaulting to @latest.
What it helps with
- build and debug WebGPU rendering in browsers or Node
- assemble 3D scene hierarchies, transforms, and cameras
- bake normal and ambient occlusion maps for Blender assets
- query local vgpu API documentation and migration guides
- validate 3D asset LODs and runtime integration
Example prompts for the agent
- Check the local vgpu documentation for scene hierarchy methods
- Help me write a WGSL compute shader pipeline using vgpu
- How do I set up baking for ambient occlusion maps in Blender for vgpu?
How to install vgpu
1Skills CLI (Vercel)
npx skills add vercel-labs/vgpu --skill vgpu -a claude-code2Manually: put the files in place
~/.claude/skills/vgpu/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vgpu/
1Skills CLI (Vercel)
npx skills add vercel-labs/vgpu --skill vgpu -a codex2Manually: put the files in place
.agents/skills/vgpu/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add vercel-labs/vgpu --skill vgpu -a cursor2Manually: put the files in place
.cursor/skills/vgpu/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install vercel-labs/vgpu vgpu2Manually: put the files in place
.github/skills/vgpu/SKILL.md1Skills CLI (Vercel)
npx skills add vercel-labs/vgpu --skill vgpu -a gemini-cli2Platform CLI
gemini skills install https://github.com/vercel-labs/vgpu --path skills/vgpuManually: put the files in place
.devin/skills/vgpu/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add vercel-labs/vgpu --skill vgpu -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about vgpu
How do I install vgpu in Claude Code?
Run npx skills add vercel-labs/vgpu --skill vgpu -a claude-code. The skill file will be installed to ~/.claude/skills/vgpu/SKILL.md.
What does the vgpu skill do?
It provides rules for WebGPU development, WGSL authoring, and Blender asset integration. It forces the agent to read bundled documentation from the local vgpu package.
Why does the skill avoid bare npx or bunx calls?
Commands like bare npx vgpu or bunx vgpu can fetch packages from npm when local binaries are missing. The skill insists on flags like npm exec --no -- vgpu --version to preserve the project's locked dependency version.
Source text
SKILL.md · MIT
--- name: vgpu description: >- Build, debug, test, and optimize WebGPU projects using vgpu, its CLI, or @vgpu packages. Use for vgpu API questions, WGSL workflows, browser or Node rendering, integrations, testing, performance work, and Blender asset modeling, baking, and runtime integration. --- # vgpu Treat the documentation bundled with the target project's installed `vgpu` package as the authority for that project. This skill is intentionally version-neutral: do not infer API shapes from the skill's Git revision, remembered APIs, the repository default branch, hosted docs, or a hosted MCP server when local package docs are available. The public skill install command has no branch pin: ```sh npx skills add vercel-labs/vgpu ``` ## 3D scenes If you need to work with 3D scenes, read [Scene composition](./scene.md) before implementing scene hierarchies, transforms, instances, cameras, or animation and physics integration. ## Blender assets For Blender modeling, high/low-poly workflows, normal or ambient occlusion baking, LODs, and asset validation, read [Blender assets](blender/index.md). That guide links to focused references for shape and assembly or baking diagnostics; load them when the task needs them. Its authoring guidance is independent of the vgpu version. For runtime API work, use the package docs below. ## Select the package version Run the project-local `vgpu` executable from the workspace that owns the dependency. First check the relevant package manifest and lockfile, then confirm which local CLI you resolved without allowing the package manager to download a missing command: ```sh pnpm exec vgpu --version npm exec --no -- vgpu --version ``` Use a local-only equivalent for other package managers, such as `yarn exec vgpu --version` or an already resolved `node_modules/.bin/vgpu`. Commands such as bare `npx vgpu` or `bunx vgpu` may download a missing package, so do not use them for local version discovery. npm's `--offline` is also insufficient because it can install a missing package from cache. Do not replace an installed version merely to read newer documentation. If a package manifest or lockfile selects `vgpu` but the local binary is unavailable, treat the dependency tree as incomplete rather than unversioned. Restore the project's locked dependencies when installation is within scope. For read-only access, the exact selected version can be invoked explicitly instead: ```sh npx -y vgpu@<selected-version> docs cat getting-started.md ``` Do not substitute `@latest` for a selected stable, RC, or other prerelease. Only when neither the project nor the user has selected a vgpu version, default to the explicit stable tag: ```sh npx -y vgpu@latest docs cat getting-started.md ``` When adding a previously unselected dependency is part of the requested work, install `vgpu@latest` with the project's package manager. Use `vgpu@next`, an RC, or any other prerelease only when the user or the existing project explicitly selected that prerelease; preserve an exact requested version. ## Route through the bundled docs Ask the resolved local CLI what documentation its version supports, then load only the pages needed for the task: ```sh pnpm exec vgpu docs --help pnpm exec vgpu docs ls pnpm exec vgpu docs cat getting-started.md pnpm exec vgpu docs find "<topic, symbol, or error code>" pnpm exec vgpu docs grep -i "<term>" pnpm exec vgpu docs cat "<path or symbol>" ``` Adapt `pnpm exec` to a no-install command for the project's package manager, but keep using its local binary; with npm, retain `npm exec --no -- vgpu` for every docs command. Start with getting started for unfamiliar projects, use `find` for task or symbol discovery, use `grep` for details mentioned inside pages, and `cat` every relevant guide and API page before changing code. Let `docs --help` from that installed version define the available commands. When upgrading a project, record its previous version before changing dependencies. After selecting the authorized target version, run `docs ls /migrations` through that version's local CLI and read the intervening version guides in order. Each guide identifies affected usage and verification steps; skip changes already applied, including when moving between RCs of the same release. Older packages may not bundle migration guides: report that absence and consult the exact release's notes instead of silently substituting the current hosted docs. For MCP-based lookup, start `vgpu mcp` through the same project-local executable so it serves the same bundled corpus. A hosted MCP server is a convenience for current stable documentation, not the authority for a project pinned to another version. If the installed docs do not contain a proposed API or workflow, do not invent it or silently switch versions. Report the mismatch and change versions only when the user's task authorizes it.
© vercel-labs · MIT · vercel-labs/vgpu