> browse/registry

> ai-ml

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

> book-sft-pipeline

This skill should be used when the user asks to "fine-tune on books", "create SFT dataset", "train style model", "extract ePub text", or mentions style transfer, LoRA training, book segmentation, or author voice replication.

> computer-vision-expert

Design, implement, debug, and review computer vision systems in Python, including image processing, detection, segmentation, classification, tracking, OCR, camera pipelines, and dataset-driven evaluation. Use when working with OpenCV, PyTorch vision models, video/image analysis, model-selection tradeoffs, annotation strategy, failure analysis, or CV performance and robustness problems.

> fireworks-ai

Expert guidance for Fireworks AI, the platform for running open-source LLMs (Llama, Mixtral, Qwen, etc.) with enterprise-grade speed and reliability. Helps developers integrate Fireworks' inference API, fine-tune models, and deploy custom model endpoints with function calling and structured output support.

> onnx

Open Neural Network Exchange format for model interoperability across frameworks. Export models from PyTorch, TensorFlow, and other frameworks to ONNX, optimize with ONNX Runtime, and deploy for cross-platform inference on CPU, GPU, and edge devices.

> gradio

Python library for building ML demo UIs with minimal code. Create interactive web interfaces for models with text, image, audio, and video inputs/outputs. Share demos via public links or deploy to Hugging Face Spaces.

> peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when a user asks to fine-tune a language model, train a custom LLM, adapt a model to their data, use LoRA or QLoRA, fine-tune Llama or Mistral, or train a model on consumer GPUs. Covers PEFT methods for 7B-70B parameter models.

> scikit-learn

Assists with building, evaluating, and deploying machine learning models using scikit-learn. Use when performing data preprocessing, feature engineering, model selection, hyperparameter tuning, cross-validation, or building pipelines for classification, regression, and clustering tasks. Trigger words: sklearn, scikit-learn, machine learning, classification, regression, pipeline, cross-validation.

> comet-ml

Expert guidance for Comet ML, the platform for tracking machine learning experiments, managing models, and monitoring production ML systems. Helps developers log experiments, compare model versions, and build reproducible ML pipelines with automatic code/data versioning.

> gcp-bigquery

Analyze massive datasets with Google BigQuery. Run SQL queries on petabytes of data, load and stream data in real-time, create materialized views, and use BigQuery ML for machine learning models directly in SQL.

> huggingface

Work with Hugging Face's ecosystem for machine learning — transformers library, model hub, tokenizers, inference pipelines, and fine-tuning. Covers downloading pre-trained models, running inference, training custom models, and publishing to the Hub.

> ollama-sdk

You are an expert in Ollama, the tool for running open-source LLMs locally. You help developers run Llama, Mistral, Gemma, Phi, CodeLlama, and other models on their machine with a simple CLI and REST API — enabling private AI development, offline inference, fine-tuning experiments, and cost-free prototyping without sending data to cloud APIs.

> pinecone

Pinecone is a managed vector database for AI and machine learning applications. Learn to create indexes, upsert embeddings, query by similarity, use namespaces and metadata filtering for semantic search and RAG pipelines.

> pytorch

Assists with building, training, and deploying neural networks using PyTorch. Use when designing architectures for computer vision, NLP, or tabular data, optimizing training with mixed precision and distributed strategies, or exporting models for production inference. Trigger words: pytorch, torch, neural network, deep learning, training loop, cuda.

> replicate

Run machine learning models in the cloud via API. Access thousands of open-source models for image generation, language, audio, and video. Fine-tune models on custom data and deploy custom models with Cog packaging format.

> tensorflow

You are an expert in TensorFlow, Google's open-source machine learning framework. You help developers build, train, and deploy neural networks using Keras (TensorFlow's high-level API), custom training loops, TensorFlow Serving for production inference, TFLite for mobile/edge deployment, and TensorFlow.js for browser ML — from prototyping to production-scale distributed training.

> together-ai

Cloud platform for running open-source AI models. Provides inference APIs for LLMs, image models, and embedding models. Supports fine-tuning on custom data, OpenAI-compatible API format, and competitive pricing for open-source model hosting.

> triton

NVIDIA Triton Inference Server for deploying AI models at scale. Supports multiple frameworks (ONNX, TensorRT, PyTorch, TensorFlow), model ensembles, dynamic batching, model versioning, and GPU/CPU inference with high throughput and low latency.

> ollama

Run LLMs locally with Ollama. Use when a user asks to run AI models locally, self-host a language model, use LLaMA or Mistral on their machine, run offline AI, build a local chatbot, avoid sending data to cloud AI providers, generate text without API costs, fine-tune or customize local models, or set up a private AI inference server. Covers model management, API usage, Modelfile customization, GPU acceleration, and integration with LangChain and other frameworks.

> kaggle-finetune

End-to-end workflow for fine-tuning LLMs using Kaggle datasets. Use when downloading datasets from Kaggle for model training, preparing conversation/customer service data for chatbot fine-tuning, or building domain-specific AI assistants. Covers dataset discovery, download, preprocessing into chat format, and integration with PEFT/LoRA training.