Skip to content
InfratoApp
InfratoApp / Resources / Agent skills / huggingface-zerogpu

huggingface-zerogpu

huggingface-zerogpu is an agent skill published by huggingface, listed under review & testing. It lives in the huggingface/skills repository, which has 11,213 GitHub stars and is licensed under Apache-2.0; we last read it on 2026-09-16.

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.

Install

skills is a generic installer for any repository of Claude agent skills -- it reads huggingface/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.

npx skills add huggingface/skills

Maintenance

Stars
11213
State
listed
Licence
Apache-2.0
From the repository

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.

huggingface-zerogpu compared with similar skills

huggingface-zerogpu compared with other skills for the same job, by publisher, what it does, repository stars and last update
SkillPublisherWhat it doesRepo starsLast update
huggingface-zerogpu (this page)huggingfaceAI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing co…11,2132026-10-23
code-reviewmattpocockReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does t…303,5492026-10-22
scaffold-exercisesmattpocockCreate exercise directory structures with sections, problems, solutions, and explainers that pass linting. Us…303,5492026-10-22
tddmattpocockTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-gree…303,5492026-10-22
webapp-testinganthropicToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend…183,8452026-10-09
browser-testing-with-devtoolsaddyosmaniTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browse…110,6112026-10-13
code-review-and-qualityaddyosmaniConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself,…110,6112026-10-13

Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.

Common questions about huggingface-zerogpu

What does huggingface-zerogpu do?
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
How do I install huggingface-zerogpu?
Run npx skills add huggingface/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
Who publishes huggingface-zerogpu?
huggingface.
Is huggingface-zerogpu maintained, and what licence does it use?
Its repository has 11,213 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-23. The repository declares the Apache-2.0 licence.

More agent skills for review & testing

All review & testing entries →

Learn this on Infrato