huggingface-zerogpu

huggingface/skillsOfficial collectionAI & ML engineering

huggingface-zerogpu is a skill in huggingface/skills, last changed 20 May 2026. It can download software, run shell commands, reach the network and name web addresses — read the findings before installing.

From the author

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 much a skill can do, not whether it is risky.

Pattern check

1 item to review

Download piped into a shell

R01 · Critical · references/cuda-and-deps.md:58

Commit 25910b3 · 3 Nov 2026

How the check works

Pattern check:1 item to reviewSee it

Install

Each tab says whether it installs commit 25910b3, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. huggingface/skills/skills/huggingface-zerogpu (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Read this before installing: Download piped into a shell — references/cuda-and-deps.md:58

Pinned to commit 25910b3, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&mkdir -p .claude/skills &&mkdir .claude/skills/huggingface-zerogpu &&cp -R "$tmp"/skills/huggingface-zerogpu/. .claude/skills/huggingface-zerogpu/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs

Pinned to commit 25910b3, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make huggingface-zerogpu.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&out="$(mktemp -d)" &&cp -R "$tmp"/skills/huggingface-zerogpu "$out"/huggingface-zerogpu &&(cd "$out" && zip -qr - huggingface-zerogpu) > huggingface-zerogpu.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose huggingface-zerogpu.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit 25910b3, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&mkdir -p .agents/skills &&mkdir .agents/skills/huggingface-zerogpu &&cp -R "$tmp"/skills/huggingface-zerogpu/. .agents/skills/huggingface-zerogpu/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit 25910b3, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&mkdir -p .cursor/skills &&mkdir .cursor/skills/huggingface-zerogpu &&cp -R "$tmp"/skills/huggingface-zerogpu/. .cursor/skills/huggingface-zerogpu/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit 25910b3, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&mkdir -p .github/skills &&mkdir .github/skills/huggingface-zerogpu &&cp -R "$tmp"/skills/huggingface-zerogpu/. .github/skills/huggingface-zerogpu/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install huggingface/skills skills/huggingface-zerogpu/SKILL.md@25910b3d0ba31a2ba102f901cdc9e008c278a69c --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit 25910b3, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&mkdir -p .gemini/skills &&mkdir .gemini/skills/huggingface-zerogpu &&cp -R "$tmp"/skills/huggingface-zerogpu/. .gemini/skills/huggingface-zerogpu/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/huggingface/skills.git --path skills/huggingface-zerogpu --scope workspace

Gemini CLI docs

Pinned to commit 25910b3, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/huggingface/skills.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&git -C "$tmp" sparse-checkout set -- skills/huggingface-zerogpu &&git -C "$tmp" checkout -q 25910b3d0ba31a2ba102f901cdc9e008c278a69c &&mkdir -p .agents/skills &&mkdir .agents/skills/huggingface-zerogpu &&cp -R "$tmp"/skills/huggingface-zerogpu/. .agents/skills/huggingface-zerogpu/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add huggingface/skills --skill huggingface-zerogpu

Agent Skills docs

Read SKILL.md first

Apache 2.0

Licence

11.3k

Repo stars

Folder last changed

Publisher

Files

Checked

3 Nov 2026

What it can touch

From the files and frontmatter at commit 25910b3. This is how much a skill can do, not whether it is risky.

Downloads software
It fetches programs or packages from the internet, or from a package source other than the default.
references/cuda-and-deps.md:58 (opens in a new tab)
Runs shell commands
Its instructions or files give the agent commands to run on your computer.
references/cuda-and-deps.md:58 (opens in a new tab)
Reaches the network
It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.
references/cuda-and-deps.md:58 (opens in a new tab)
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Outside links we did not follow

Pattern check

Pattern check: 1 item to review · commit 25910b3 · 3 Nov 2026

R01 · CriticalDownload piped into a shell

references/cuda-and-deps.md:58

curl -s https://pypi.org/pypi/<pkg>/<version>/json \      | python3 -c "import json,sys,re; rd=json.load(sys.stdin)['info'].get('requires_dist') or []; print('\n'.join(x for x in rd if re.match(r'^to…

We checked every text file in this skill, at commit 25910b3 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Outside links we did not follow

https://huggingface.co/docs/hub/spaces-zerogpu
https://huggingface.co/blog/zerogpu-aoti
https://github.com/Dao-AILab/flash-attention/releases
https://huggingface.co/kernels-community
https://pypi.org/pypi/
https://github.com/pytorch/torchcodec

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Note
  Line 235 has dated wording ("since 2025"), which goes stale. B8
  Fix: Describe the current way, and move old patterns into their own clearly marked section.
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
  Line 235 has dated wording ("since 2025"), which goes stale. B8
  Fix: Describe the current way, and move old patterns into their own clearly marked section.
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
  The description is 869 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
- Note
  Line 235 has dated wording ("since 2025"), which goes stale. B8
  Fix: Describe the current way, and move old patterns into their own clearly marked section.
OpenAI (Codex & API)Passes
VS Code & CopilotPasses

SKILL.md

Read SKILL.md on GitHub

Files

5 files

Path	Size
SKILL.md (opens in a new tab)	17.8 KB
references/concurrency.md (opens in a new tab)	2.5 KB
references/cuda-and-deps.md (opens in a new tab)	4.7 KB
references/how-quota-works.md (opens in a new tab)	3.8 KB
references/how-zerogpu-works.md (opens in a new tab)	4.7 KB

More from huggingface/skills

Skill	What it can touch	Pattern check	Licence	Updated
hf-cliHugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`. Downloads software +3 more Pattern check: 1 item to reviewApache 2.0Updated 29 Oct 2026	Downloads software Runs shell commands +2 more	Pattern check: 1 item to review	Apache 2.0	29 Oct 2026
hf-cloud-aws-context-discoveryDiscover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first. Touches credentials +1 more Pattern check: Nothing flaggedApache 2.0Updated 7 Jul 2026	Touches credentials Runs shell commands	Pattern check: Nothing flagged	Apache 2.0	7 Jul 2026
hf-cloud-python-env-setupSet up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs. Runs shell commands +3 more Pattern check: Nothing flaggedApache 2.0Updated 7 Jul 2026	Runs shell commands Reaches the network +2 more	Pattern check: Nothing flagged	Apache 2.0	7 Jul 2026
hf-cloud-sagemaker-deployment-plannerPlan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills. Runs shell commands Pattern check: Nothing flaggedApache 2.0Updated 3 Aug 2026	Runs shell commands	Pattern check: Nothing flagged	Apache 2.0	3 Aug 2026
hf-cloud-sagemaker-iam-preflightEnsure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions. Runs shell commands +1 more Pattern check: Nothing flaggedApache 2.0Updated 10 Sept 2026	Runs shell commands Bundles scripts	Pattern check: Nothing flagged	Apache 2.0	10 Sept 2026
hf-cloud-sagemaker-production-defaultsCreate a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments. Runs shell commands +2 more Pattern check: Nothing flaggedApache 2.0Updated 10 Sept 2026	Runs shell commands Names web addresses +1 more	Pattern check: Nothing flagged	Apache 2.0	10 Sept 2026

All skills in huggingface/skills

Other AI & ML engineering skills

Same category, most repo stars first.

Skill	What it can touch	Pattern check	Licence	Updated
agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack. affaan-m/ECC Runs shell commands Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Runs shell commands	Pattern check: Nothing flagged	MIT	11 Aug 2026
agent-evalHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression. affaan-m/ECC Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	MIT	11 Aug 2026
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-`, `us.anthropic.`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai\|langchain_openai\|google.generativeai\|genai\|mistralai\|cohere\|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). anthropics/skills Touches credentials +6 more Pattern check: 1 item to reviewApache 2.0Updated 9 Oct 2026	Touches credentials Downloads software +5 more	Pattern check: 1 item to review	Apache 2.0	9 Oct 2026
mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). anthropics/skills Touches credentials +4 more Pattern check: Nothing flaggedApache 2.0Updated 28 Oct 2026	Touches credentials Runs shell commands +3 more	Pattern check: Nothing flagged	Apache 2.0	28 Oct 2026
benchmark-modelsCross-model benchmark for gstack skills. (gstack) garrytan/gstack Touches credentials +2 more Pattern check: 1 item to reviewMITUpdated 30 Oct 2026	Touches credentials Runs shell commands +1 more	Pattern check: 1 item to review	MIT	30 Oct 2026
eval-planPreregister a paid eval (bars, arms, decoys, stop rules), dry-run it at zero cost, then run a three-item priced pilot whose spend table gates approval. (gstack) garrytan/gstack Runs shell commands +1 more Pattern check: 1 item to reviewMITUpdated 2 Nov 2026	Runs shell commands Pre-approves tools	Pattern check: 1 item to review	MIT	2 Nov 2026

At a glance

What it can touch

Pattern check

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Outside links we did not follow

Format check

SKILL.md

Files

More from huggingface/skills

Other AI & ML engineering skills