“Model inference”

Use synthetic data and back-translation with quality filters and held-out protection.

Opinionated Bayesian modeling workflow with PyMC and ArviZ.

Benchmark and A/B-test multiple LLMs or systems-under-test on one evaluation dataset.

Detect and resolve incoherence in documentation, code, specs vs implementation.

Run Gemini batch inference on Google Cloud Vertex AI.

Running AI models locally with Ollama and llama.cpp.

Hugging 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 the user asks to "design an experiment", "build a predictive model", "run A/B test analysis", "perform causal inference", "engineer features"…

Route GeoAI geospatial data, inference, training, foundation-model, and integration workflows.

Run a 3-leg evaluation against a newly released LLM.

You are an expert at Kubernetes and Gateway inference extension, architect and implement the Gateway inference extensions for Kubernetes focused on LLM…

开启“问答模式”，通过递归式提问澄清需求，实时维护 IMPLEMENTATION_PLAN.md，并在用户最终确认后执行开发任务。当用户提到“问答模式”、“执行访谈”、“需求澄清”或需要对复杂任务进行前置规划时使用。

Route Asteroid tasks to the right sub-skill for pretrained inference, training recipes, custom model building, and model sharing.

Guides Earth2Studio weather and climate inference workflows, data access, model and component selection, output/checkpoint handling, extension, and optional…

Pick the right serving container for a SageMaker model deployment and find its current image URI.

Routes official FlashVSR diffusion-based streaming video super-resolution setup, model preparation, and CUDA inference for v1 and v1.1.

Implement "Sign In with OpenRouter" using OAuth PKCE — framework-agnostic, no SDK or client registration required.

Use when researching another Git repository

Discovers and evaluates scientific datasets, models, methodology posts, and Spaces through the Hugging Science catalog.

Package, preflight, run, validate, or troubleshoot NVIDIA Alpamayo 2 Super 34B VLA inference in NPA, including its OpenMDW model terms, separately gated…

Apply HeritageLink's allowlisted local inference policy before recommendation.

Static type inference and validation for navigation paths

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA.

Routes easy12306 12306 captcha recognition tasks across pretrained inference, data preparation, text-model training, and image-model training workflows.