zerogpu

Show how much you've saved by routing tasks to ZeroGPU instead of your frontier model — a rounded dollar estimate and the frontier-model tokens offloaded. Use when the user asks how much they've saved, their ZeroGPU savings, or to see the cost-savings summary.

Sign in to ZeroGPU and persist the API key. Use when the user asks to log in, authenticate, or set up ZeroGPU credentials for the first time.

Sign in to ZeroGPU and persist the API key. Use when the user asks to log in, authenticate, or set up ZeroGPU credentials for the first time.

Zero-shot classification against a caller-supplied list of candidate labels (deberta-v3-small). Use when the user wants to classify text into a custom set of labels they provide (e.g. "is this positive, negative, or neutral?", "tag this as bug, feature, or question").

Short chat reply via the ZeroGPU edge model (LFM2.5-1.2B-Instruct). Use when the user wants a quick, single-turn answer that does not need host-level reasoning, prior conversation context, or code generation. Optional system instructions via -i.

Chat with ZeroGPU's Thinking variant (LFM2.5-1.2B-Thinking), which returns visible reasoning alongside the answer. Use when the user wants the model's reasoning shown, or asks a short logic/math/word-problem question that benefits from step-by-step output.

Enriched IAB classification — returns audience categories plus topics, keywords, and inferred intent. Use when the user wants richer ad/audience signals than plain IAB labels (e.g. "give me topics, keywords, and intent for this passage").

Classify text against the IAB content/audience taxonomy. Use when the user asks for IAB categories, ad-taxonomy labels, or "what topic is this article about" against a standard taxonomy.

Add or document a third-party integration in the ZeroGPU docs (integrations/ pages, docs.json nav, and the index card grids). Use this skill whenever the user asks to "add an integration", "document an integration for X", "create an integration page", "move X out of Coming Soon", or otherwise wires a new platform/SDK/framework into the /integrations/ tab. Encodes the repo's required page structure so the new page, the index card, and the nav entry all stay in sync.

Author a notebook-style cookbook `.mdx` page under `cookbook/` that walks a reader end-to-end through combining ZeroGPU with another framework, platform, or SDK (CAMEL, LangChain, LlamaIndex, CrewAI, AutoGen, a Claude Code plugin, an Electron app, etc.). The skill encodes the established cookbook template: emoji-headed sections, "In this notebook, you'll explore:" tool bullets, `getpass` key setup, alternating prose-and-code cells with illustrative outputs, a `🌟 Highlights` recap, and the canonical ZeroGPU blurb. Use this skill whenever the user asks to "create a cookbook", "write a cookbook for X with ZeroGPU", "draft a cookbook combining X and ZeroGPU", "add a tutorial notebook for X", or otherwise wants a notebook-style integration walkthrough authored in ZeroGPU's cookbook voice and structure.

Generate a ready-to-paste YouTube title and description for a ZeroGPU video, anchored to a specific docs page (an integration, cookbook, model, or concept) with correct, verified links pulled from the repo. Use this skill whenever the user asks to "create a YouTube description", "write a video description", "make a description for my YouTube video", "give me a title and description for this video", or is recording/posting a video about a ZeroGPU feature and needs the description box content. Encodes the repo's canonical links and the established description layout so every link resolves and nothing is invented.