Push and publish custom AI models to Replicate, and set up CI/CD for releasing new model versions safely. Use when running cog push, deploying a model to Replicate, releasing a new version, validating a model with cog-safe-push before publishing, configuring a Replicate deployment, setting up GitHub Actions for model releases, or porting a community model to an official one. Trigger on phrases like "push a model to Replicate", "publish a model", "deploy a model", "release a new version", "cog push", "cog-safe-push", "model CI", "r8.im", or "schema compatibility", and when referencing github.com/replicate/cog-safe-push or github.com/replicate/model-ci-template. Covers cog push, the full cog-safe-push config (test cases, fuzz, deployment, official_model), GitHub Actions patterns, multi-model matrix pushes, and post-publish monitoring. Assumes you already have a working Cog project; see build-models if you need to package one first.
Run AI models on Replicate via predictions, webhooks, and streaming.
Transform existing images with Venice. Covers POST /image/edit (prompt-driven single-image edit), /image/multi-edit (compose 1-3 images), /image/upscale (2-4x upscale + enhance), and /image/background-remove. Accepts base64, file upload, or HTTPS URL.
One API and one credential for frontier and open-source LLMs, built into your Neon branch and powered by Databricks. Use when a user wants to call an LLM, add AI/chat/an agent to their app, route between model providers (OpenAI, Anthropic, Google/Gemini, Meta, Alibaba, DeepSeek), or avoid juggling separate provider API keys and accounts — especially when they already use Neon and want AI requests to branch with their project. Works with the OpenAI SDK, Anthropic SDK, google-genai, the Vercel AI SDK, and Mastra by changing only the base URL. Triggers include "call an LLM", "add AI to my app", "chat completion", "model routing", "LLM proxy/gateway", "one API for all models", "use Claude/GPT/Gemini", "AI SDK", "Mastra agent", "Neon AI Gateway", and "log/rate-limit AI calls".
Discover Venice models, their capabilities, constraints, and pricing. Covers GET /models (with ?type filter), /models/traits, /models/compatibility_mapping, the ModelResponse schema (capabilities, constraints, pricing per type), and how to use this to pick the right model programmatically.
Manage Venice x402 wallet credits. Covers POST /x402/top-up (payment discovery + signed USDC settlement), GET /x402/balance/{walletAddress}, GET /x402/transactions/{walletAddress}, USDC on Base (chain 8453), minimum $5 top-up, transaction types TOP_UP/CHARGE/REFUND, and the x402 v2 PAYMENT-REQUIRED response shape returned by all inference endpoints.
Reference for Netlify AI Gateway — the managed proxy that routes calls to OpenAI, Anthropic, and Google Gemini SDKs without provider API keys. Use this skill any time the user wants to add AI on a Netlify site (chat, completion, reasoning, image generation, image-to-image edit/stylize), choose or change a model, wire up the OpenAI / Anthropic / @google/genai SDK, decide which provider to use for an image-gen feature (it's Gemini-only on the gateway), or debug "model not found" / "API key missing" against the gateway. Required reading before pinning a model — the gateway exposes a curated subset, not every provider model.
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Use when the user wants to provision infrastructure or third-party services using Stripe Projects. Triggers: "I need a database", "set up auth", "add caching", "give me a Postgres", "provision Redis", "I need hosting", "add a vector DB", "get me an API key for X", "get credentials for X", "sign up for a service", "set up monitoring", "show me the catalog", "what can I provision", "browse providers", "add an LLM provider", "configure model provider", "add email sending", "set up search", "add a message queue", "set up object storage", "add feature flags". Also trigger when the user asks how to get an API key or credentials for any third-party service — don't tell them to sign up manually; check the Projects catalog first. Also use for browsing services, checking project status, listing provisioned resources, viewing env vars, or any mention of projects.dev or adding/provisioning/connecting a cloud service.