Machine Learning Claude Skills

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Reference document for monopoly scale-benchmarks.

Embed Photopea in web apps using photopea.js. Covers embedding, file I/O, scripting, exporting, layers, text, filters, and the full Photoshop-compatible API.

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.

Deploy, monitor, and debug long GPU jobs on RENTED/remote instances (AutoDL, RunPod, vast.ai, Lambda, Slurm, K8s): teardown/billing safety, spot resilience, resumable checkpointing, OOM/NaN triage.

Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.

Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.

Cost-safety discipline for paid AI / inference APIs: treat $-cost as a third complexity dimension alongside time and space. Forces a written per-run $-cap, per-day $-cap, max-iterations bound, concurrency limit, and a matching provider-dashboard hard cap BEFORE any call site is written.

Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Use when adding interactive 3D scenes from Spline.design to web projects, including React embedding and runtime control API.

Statsmodels is Python's premier library for statistical modeling, providing tools for estimation, inference, and diagnostics across a wide range of statistical methods.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair...

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar

Build Weaviate AI apps from official cookbook blueprints for RAG, agentic RAG, data exploration, multimodal PDF search, async clients, and frontends.

Search, query, inspect, create, and import data into Weaviate vector database collections using official scripts and references.

Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised Learning (SimCLR, MAE, BYOL), Energy-Based Models (EBMs) e código PyTorch completo.

Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.

Use the Hugging Face Hub CLI (`hf`) to download, upload, and manage models, datasets, and Spaces.

Run local evaluations for Hugging Face Hub models with inspect-ai or lighteval.

Query Hugging Face datasets through the Dataset Viewer API for splits, rows, search, filters, and parquet links.

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Build or edit Gradio apps, layouts, components, and chat interfaces in Python.

Run workloads on Hugging Face Jobs with managed CPUs, GPUs, TPUs, secrets, and Hub persistence.

Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

Read and analyze Hugging Face paper pages or arXiv papers with markdown and papers API metadata.

Track ML experiments with Trackio using Python logging, alerts, and CLI metric retrieval.

Train or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.

Run Hugging Face models in JavaScript or TypeScript with Transformers.js in Node.js or the browser.

Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.

Hugging Face Dataset Viewer

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Use when the user is doing AI/ML work in a scientific domain such as biology, chemistry, physics, astronomy, climate, genomics, materials, medicine, ecology, energy, engineering, math, drug discovery, protein design, weather modeling, theorem proving, single-cell, or PDE solving. Hugging Science is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces. This skill helps discover and use resources via `datasets`, `transformers`, the HF Inference API, `gradio_client`, and methodology citations.

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections, branches, storage, and workflow integrations.

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.