Machine Learning

Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasks involve model extraction attacks, recovering hidden layer weights from neural networks, or reverse-engineering ReLU network parameters from query access.

Score de risco social e recomendações proativas

Find marker genes and annotate cell types in single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for differential expression between clusters, identifying cluster-specific markers, scoring gene sets, and assigning cell type labels.

Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.

Detect chromatin loops and point interactions from Hi-C data using cooltools, chromosight, and HiCCUPS-like methods. Identify CTCF-mediated loops and enhancer-promoter contacts. Use when detecting chromatin loops from Hi-C data.

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.

Profile JAX training using xprof/TensorBoard/Perfetto and analyze hotspots. Use when asked to profile, benchmark, or optimize training throughput.

Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, cloud-native workflows (STAC, COG, Planetary Computer), and 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Predict project completion dates using ML models. Forecast schedule delays based on current progress, historical patterns, and risk factors.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Bayesian statistical modeling with PyMC v5+. Use when building probabilistic models, specifying priors, running MCMC inference, diagnosing convergence, or comparing models. Covers PyMC, ArviZ, pymc-bart, pymc-extras, nutpie, and JAX/NumPyro backends. Triggers on tasks involving: Bayesian inference, posterior sampling, hierarchical/multilevel models, GLMs, time series, Gaussian processes, BART, mixture models, prior/posterior predictive checks, MCMC diagnostics, LOO-CV, WAIC, model comparison, or causal inference with do/observe.

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Builds and deploys data processing and ML training pipelines using TrueFoundry Workflows (built on Flyte). Use when creating DAGs, orchestrating multi-step tasks, scheduling ETL pipelines, or running ML training workflows.

Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.

Evaluate AI systems for fairness using demographic parity, equalized odds, and bias detection techniques with mitigation strategies.

Q-learning, DQN, PPO, A3C, policy gradient methods, multi-agent systems, and Gym environments. Use for training agents, game AI, robotics, or decision-making systems.

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),...

MLflow — tracking, Model Registry, GenAI evaluation, tracing, S3/RDS backend, framework integrations. Use when setting up experiment tracking or model management. NOT for W&B.

Deploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency serving, or encountering cache invalidation, experiment tracking, quality monitoring issues.

Separates T and non-T cells or B and non-B cells from a mixed cell population. Uses either clonotype percentage from VDJ data, indicator gene expression (CD3 markers for T cells, CD19/CD20 for B cells), custom selector expressions, or k-means clustering for automatic selection.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

RL training reference for the ART framework. Use when the user asks to create, write, or help with an RL training script, reinforcement learning, GRPO, reward functions, RULER scoring, rollout functions, or anything related to RL fine-tuning.

When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

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.

Expert skill for multi-sensor fusion and state estimation using Kalman filtering. Implement EKF/UKF, configure robot_localization, fuse IMU, GPS, odometry, and visual sensors for robust localization.

Rapid pathogen characterization and drug repurposing analysis for infectious disease outbreaks. Identifies pathogen taxonomy, essential proteins, predicts structures, and screens existing drugs via docking. Use when facing novel pathogens, emerging infections, or needing rapid therapeutic options during outbreaks.

Enforces baseline comparisons, cross-validation, interpretation, and leakage prevention for ML pipelines

Integrate and analyze multiple omics datasets (transcriptomics, proteomics, epigenomics, genomics, metabolomics) for systems biology and precision medicine. Performs cross-omics correlation, multi-omics clustering (MOFA+, NMF), pathway-level integration, and sample matching. Coordinates ToolUniverse skills for expression data (RNA-seq), epigenomics (methylation, ChIP-seq), variants (SNVs, CNVs), protein interactions, and pathway enrichment. Use when analyzing multi-omics datasets, performing integrative analysis, discovering multi-omics biomarkers, studying disease mechanisms across molecular layers, or conducting systems biology research that requires coordinated analysis of transcriptome, genome, epigenome, proteome, and metabolome data.

Analyze spatial transcriptomics data to map gene expression in tissue architecture. Supports 10x Visium, MERFISH, seqFISH, Slide-seq, and imaging-based platforms. Performs spatial clustering, domain identification, cell-cell proximity analysis, spatial gene expression patterns, tissue architecture mapping, and integration with single-cell data. Use when analyzing spatial transcriptomics datasets, studying tissue organization, identifying spatial expression patterns, mapping cell-cell interactions in tissue context, characterizing tumor microenvironment spatial structure, or integrating spatial and single-cell RNA-seq data for comprehensive tissue analysis.

Implement a new model architecture using the Surogate Python DSL. Use when the user wants to add support for a new HuggingFace model (e.g., "add Gemma2 support", "implement DeepSeek model", "add new architecture"). Guides through creating block, model, and HF mapping definitions.

Master A2C, A3C, SAC, TD3 - actor-critic methods for continuous control

Validate feature store data quality before model training

Comprehensive best practices for robot perception systems covering cameras, LiDARs, depth sensors, IMUs, and multi-sensor setups. Use this skill when working with RGB image processing, depth maps, point clouds, sensor calibration (intrinsic, extrinsic, hand-eye), object detection, semantic segmentation, 3D reconstruction, visual servoing, or perception pipeline optimization. Trigger whenever the user mentions OpenCV, Open3D, PCL, RealSense, ZED, OAK-D, camera calibration, AprilTags, ArUco markers, stereo vision, RGBD, point cloud filtering, ICP registration, coordinate transforms, camera intrinsics, distortion correction, image undistortion, sensor streaming, frame synchronization, or any computer vision task in a robotics context. Also covers multi-camera rigs, time synchronization across sensors, perception latency budgets, and production deployment of perception pipelines.

Machine learning and analytics patterns in Azure Data Factory - orchestrating Azure ML batch endpoints (SDK v2), Azure OpenAI Batch API for LLM scoring, Azure AI Services (Microsoft Foundry), Databricks ML, Azure SQL to Storage archival for analysis, and feature engineering with Data Flows

Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018. Use quando quiser: perspectivas sobre deep learning e visão...

Comprehensive guide for Qiskit - IBM's quantum computing framework. Use for quantum circuit design, quantum algorithms (VQE, QAOA, Grover, Shor), quantum simulation, noise modeling, quantum machine learning, and quantum chemistry calculations. Essential for quantum computing research and applications.

Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease/condition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis across 9 phases covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity/DDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment (Low/Intermediate/High/Very High), treatment algorithm (1st/2nd/3rd line), pharmacogenomic guidance, clinical trial matches, and monitoring plan. Use when clinicians ask about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy across cancer, metabolic, cardiovascular, neurological, or rare diseases.

Comprehensive antibody engineering and optimization for therapeutic development. Covers humanization, affinity maturation, developability assessment, and immunogenicity prediction. Use when asked to optimize antibodies, humanize sequences, or engineer therapeutic antibodies from lead to clinical candidate.

Predict pump.fun token graduations (YES/NO) on Solana mainnet via PumpMarket parimutuel betting markets.

ToolUniverse workflow — Multiomic Disease Characterization

Causal inference and discovery for RAN optimization with Graphical Posterior Causal Models (GPCM), intervention effect prediction, and causal relationship learning. Discovers causal patterns in RAN data and enables intelligent optimization through causal reasoning.

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks. Use quando quiser: perspectivas históricas sobre deep...

Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps Trigger terms: machine learning, ML, AI, model training, MLOps, model deployment, feature engineering, model evaluation, neural network, deep learning Use when: User requests involve ai ml engineer tasks.

Expert knowledge for Azure Machine Learning development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building, debugging, or optimizing Azure Machine Learning applications. Not for Azure Databricks (use azure-databricks), Azure Synapse Analytics (use azure-synapse-analytics), Azure HDInsight (use azure-hdinsight), Azure Data Science Virtual Machines (use azure-data-science-vm).

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention