Database

Expert guidance for video understanding, object tracking, action recognition, and real-time video processing. Covers SORT, DeepSORT, ByteTrack, SlowFast, optical flow, and scalable video pipelines. Trigger: video analysis, object tracking, multi-object tracking, action recognition, video classification, optical flow, surveillance, video processing, MOT.

Designing computer vision pipelines for image and video analysis tasks. Covers classification, object detection, segmentation, data augmentation, and model optimization. Trigger keywords: computer vision, image classification, object detection, segmentation, image processing, CNN, vision transformer.

Systematic approach to data cleaning, transformation, and feature preparation for machine learning. Covers missing values, encoding, scaling, outlier handling, and feature engineering. Trigger keywords: data cleaning, preprocessing, feature engineering, data preparation, ETL for ML.

ML model deployment and MLOps practices for production systems. Covers serving infrastructure, model versioning, monitoring, CI/CD for ML, and A/B testing. Trigger keywords: ML deployment, MLOps, model serving, production ML, model monitoring, ML pipeline, model registry.

Comprehensive model evaluation and metrics selection for machine learning. Covers classification, regression, ranking metrics, cross-validation strategies, and statistical testing. Trigger keywords: model evaluation, metrics, accuracy, F1 score, AUC, cross-validation, model comparison.

Guides you through choosing the right machine learning model for a given problem. Covers supervised, unsupervised, and reinforcement learning paradigms with decision criteria based on data characteristics, performance requirements, and constraints. Trigger keywords: model selection, algorithm choice, ML approach, which model.

Guides the design of neural network architectures for various tasks. Covers layer selection, depth/width tradeoffs, activation functions, regularization, and modern architecture patterns. Trigger keywords: neural network design, deep learning architecture, CNN, transformer, network topology.

Designing end-to-end natural language processing pipelines from text ingestion to model serving. Covers tokenization, embeddings, transformer models, and task-specific architectures. Trigger keywords: NLP pipeline, text processing, language model, text classification, NER, sentiment analysis.

Advanced prompt engineering techniques for large language models. Covers structured prompting, chain-of-thought, few-shot examples, system prompts, and output control. Trigger keywords: prompt design, LLM prompting, prompt optimization, prompt template.

Guide for reinforcement learning systems where agents learn through environment interaction and reward signals. Use when designing RL pipelines, selecting algorithms, or building reward functions. Trigger keywords: reinforcement learning, RL, reward shaping, policy gradient, Q-learning, multi-armed bandit, MDP.

Techniques for predicting future values from sequential temporal data. Use when building forecasting models, analyzing trends, or handling seasonality. Trigger keywords: time series, forecasting, ARIMA, prophet, seasonal decomposition, trend analysis, temporal prediction.

Design and maintain continuous integration and continuous delivery pipelines that automate build, test, and deployment workflows. Trigger keywords: CI/CD, pipeline, GitHub Actions, Jenkins, GitLab CI, build automation, deployment pipeline.

Design scalable, resilient, and cost-effective systems on cloud platforms like AWS, GCP, and Azure. Trigger keywords: cloud architecture, AWS, GCP, Azure, well-architected, multi-region, high availability, cloud-native.

Manage system configurations consistently across environments using automation tools. Trigger keywords: configuration management, Ansible, Puppet, Chef, Salt, system configuration, desired state, idempotent.

Manage containerized applications at scale using orchestration platforms like Kubernetes, Docker Swarm, and ECS. Trigger keywords: Kubernetes, k8s, container orchestration, Docker, pods, services, deployments, Helm, ECS.

Reduce and optimize cloud infrastructure spending without sacrificing performance or reliability. Trigger keywords: cloud costs, cost optimization, FinOps, reserved instances, spot instances, rightsizing, cloud billing.

Coordinate effective incident response from detection through resolution and post-mortem. Trigger keywords: incident management, incident response, on-call, postmortem, blameless, severity levels, war room, MTTR.

Provision and manage cloud infrastructure through code rather than manual configuration. Covers Terraform, Pulumi, CloudFormation, and IaC best practices. Trigger keywords: IaC, Terraform, infrastructure as code, CloudFormation, Pulumi, provisioning, state management.

Build observability systems using metrics, logs, and traces to understand system behavior and diagnose issues. Trigger keywords: monitoring, observability, metrics, logging, tracing, Prometheus, Grafana, Datadog, alerting, SLO, SLI.

Integrate security practices into DevOps workflows and CI/CD pipelines. Covers shift-left security, vulnerability scanning, and secure development lifecycle. Trigger keywords: DevSecOps, security automation, vulnerability scanning, SAST, DAST, supply chain security, shift-left.

Implement service mesh infrastructure for managing microservice communication, observability, and security. Trigger keywords: service mesh, Istio, Linkerd, Envoy, sidecar proxy, mTLS, traffic management, circuit breaker.

Understand DNS, domain management, CDNs, SSL/TLS, load balancing, and web hosting fundamentals. Use this skill when the user asks about setting up a domain, configuring DNS records, understanding how websites are served, choosing hosting, setting up HTTPS, or troubleshooting domain and DNS issues.

Craft effective prompts for AI image generation models to produce high-quality visual outputs. Use this skill when the user asks about creating AI-generated images, writing image prompts, improving their generated image results, or wants guidance on composition, style references, negative prompts, or iterating on visual outputs from any text-to-image system.

Guides the design and development of AI-powered products. Trigger when users ask about UX for AI features, handling AI uncertainty in products, human-in-the-loop design, AI failure modes, building user trust in AI, AI ethics in products, or designing AI-first experiences. Covers the intersection of product thinking, user experience, and AI capabilities.

Guides exploratory data analysis, statistical methods, and insight extraction. Trigger when users ask about EDA, data cleaning, pandas or SQL patterns, hypothesis testing, summary statistics, data profiling, outlier detection, or extracting insights from datasets. Covers practical analysis workflows from raw data to actionable findings.

Guides data visualization design, chart selection, and dashboard creation. Trigger when users ask about choosing chart types, dashboard design, storytelling with data, color palettes for data, visualization libraries, Matplotlib, Plotly, D3, or presenting data effectively. Covers principles of visual communication and practical implementation.

Guides A/B testing, experimentation design, and statistical analysis of experiments. Trigger when users ask about A/B tests, statistical significance, sample size calculation, experiment design, randomization, multivariate testing, experiment analysis, or common experimentation pitfalls. Covers the full experimentation lifecycle from hypothesis to decision.

Guides feature engineering for machine learning models. Trigger when users ask about feature selection, feature transformation, encoding categorical variables, creating temporal features, text feature extraction, feature stores, or preparing data for ML models. Covers practical patterns for turning raw data into predictive signals.

Guides model fine-tuning decisions, data preparation, and training strategies. Trigger when users ask about fine-tuning LLMs, when to fine-tune vs use prompting, training data preparation, LoRA and parameter-efficient fine-tuning, evaluation of fine-tuned models, deployment of custom models, or cost optimization for fine-tuning. Covers the full lifecycle from decision to production.

Guides ML model evaluation, metrics selection, and monitoring. Trigger when users ask about choosing evaluation metrics, cross-validation strategies, detecting model bias, fairness in ML, A/B testing models in production, monitoring model drift, or understanding model performance. Covers rigorous evaluation from development through production.

Guides end-to-end ML pipeline design and MLOps implementation. Trigger when users ask about building ML pipelines, data ingestion, feature engineering workflows, model training infrastructure, model deployment, model monitoring, CI/CD for ML, or MLOps best practices. Covers orchestration, reproducibility, and production-grade machine learning systems.

Design effective prompts for large language models to produce accurate, consistent, and useful outputs. Use this skill when the user asks about writing better prompts, improving LLM outputs, using chain-of-thought reasoning, few-shot examples, system prompts, or wants guidance on advanced prompting techniques for any AI language model.

Guides LLM prompt design and optimization. Trigger when users ask about writing system prompts, few-shot learning, chain of thought prompting, structured output from LLMs, prompt evaluation, prompt templates, or optimizing LLM behavior. Covers practical prompt patterns for building reliable AI applications.

Guides Retrieval Augmented Generation system design and implementation. Trigger when users ask about RAG pipelines, chunking strategies, embedding models, vector databases, semantic search, hybrid search, retrieval quality, document processing, or knowledge base systems. Covers the full RAG stack from document ingestion to answer generation.

Triggers when users need help with analytics engineering, dbt, dbt models, tests, macros, packages, incremental models, semantic layer, metrics definitions, documentation-as-code, CI/CD for data transformations, data mesh, self-serve analytics, or reverse ETL. Activate for questions about building dbt projects, designing transformation layers, implementing metrics layers, or enabling self-service data access.

Triggers when users need help with Apache Spark, batch data processing, RDDs, DataFrames, Catalyst optimizer, partitioning strategies, shuffle optimization, memory tuning, Spark SQL, data skew handling, broadcast joins, adaptive query execution, PySpark best practices, or cluster sizing. Activate for questions about Spark job optimization, batch ETL performance, distributed data processing, or large-scale data transformation.

Triggers when users need help with data governance, data cataloging, DataHub, Amundsen, OpenMetadata, data lineage tracking, access control policies, PII detection, data classification, retention policies, regulatory compliance (GDPR, CCPA, HIPAA), data stewardship, or metadata management. Activate for questions about organizing data assets, tracking data lineage, managing data access, handling sensitive data, or meeting regulatory requirements.

Triggers when users need help with data integration, Change Data Capture (CDC), Debezium, Fivetran, Airbyte, API data extraction, file-based ingestion, CSV, JSON, Parquet, Avro, webhook processing, data replication, schema registry, Confluent Schema Registry, AWS Glue Schema Registry, or format selection. Activate for questions about ingesting data from external sources, choosing ingestion tools, implementing CDC, or managing data formats and schemas.

Triggers when users need help with data lake storage design, object storage (S3, GCS, ADLS), partitioning strategies, file format selection (Parquet, ORC, Avro, JSON), compression codecs (Snappy, Zstd, LZ4), small file problem, storage tiering (hot/warm/cold), lifecycle policies, or storage cost optimization. Activate for questions about organizing data on object storage, choosing file formats, optimizing storage costs, or managing data lake layout.

Triggers when users need help with lakehouse architecture, Delta Lake, Apache Iceberg, Apache Hudi, open table formats, ACID transactions on data lakes, time travel, schema enforcement vs evolution, Z-ordering, data skipping, compaction, or medallion architecture (bronze/silver/gold). Activate for questions about combining data lake and warehouse capabilities, choosing table formats, or designing lakehouse storage layers.

Triggers when users need help with data migration, large-scale migration strategies, zero-downtime migration, dual-write patterns, reconciliation, shadow traffic, cutover planning, data validation during migration, rollback strategies, cloud-to-cloud migration, or legacy system decommissioning. Activate for questions about migrating databases, moving between cloud platforms, planning migration cutovers, or decommissioning old systems.

Triggers when users need help with data modeling, dimensional modeling, Kimball vs Inmon methodology, data vault 2.0, activity schema, one big table (OBT), normalization vs denormalization, surrogate keys, conformed dimensions, fact table design, entity-relationship modeling, or choosing a modeling approach. Activate for questions about designing data models, choosing between modeling methodologies, or structuring tables for analytics.

Triggers when users need help with data orchestration, Apache Airflow, DAGs, operators, executors, sensors, Dagster, Prefect, orchestration patterns, fan-out/fan-in, conditional branching, dependency management, retry strategies, backfill operations, or pipeline monitoring and alerting. Activate for questions about scheduling data pipelines, choosing orchestration tools, designing DAG structures, or managing pipeline operations.

Triggers when users need help with data pipeline design, ETL vs ELT patterns, batch or streaming pipeline architecture, idempotency, exactly-once semantics, backfill strategies, schema evolution, pipeline orchestration, dead letter queues, or data contracts. Activate for questions about building reliable data pipelines, choosing between batch and streaming, handling pipeline failures, or designing producer-consumer data interfaces.

Triggers when users need help with data quality, data testing, data validation, Great Expectations, dbt tests, Soda, anomaly detection in data, data profiling, SLA management, circuit breakers in pipelines, data quality scoring, or data quality dimensions. Activate for questions about ensuring data reliability, building data quality frameworks, monitoring data freshness, or implementing data quality checks in pipelines.

Triggers when users need help with cloud data warehouse design, Snowflake, BigQuery, Redshift, dimensional modeling, star schema, snowflake schema, slowly changing dimensions, materialized views, query optimization, warehouse compute management, or cost control. Activate for questions about warehouse architecture, data modeling for analytics, query performance tuning, multi-cluster warehouses, or warehouse cost optimization.

Triggers when users need help with real-time analytics, real-time dashboards, OLAP engines, ClickHouse, Apache Druid, Apache Pinot, StarRocks, pre-aggregation vs on-the-fly computation, materialized views for real-time, approximate query processing, HyperLogLog, Count-Min Sketch, lambda architecture, or kappa architecture. Activate for questions about building real-time analytical systems, choosing OLAP databases, sub-second query performance, or real-time aggregation strategies.

Triggers when users need help with stream processing, Apache Kafka architecture, topics, partitions, consumer groups, exactly-once processing, Kafka Streams, Apache Flink, Spark Streaming, event sourcing, CQRS, windowing strategies, watermarks, late data handling, stream-table duality, or real-time aggregation. Activate for questions about building streaming pipelines, choosing streaming frameworks, event-driven architectures, or real-time data processing.

Triggers when users need help with adversarial machine learning, model robustness, or ML security. Activate for questions about adversarial attacks (FGSM, PGD, C&W, AutoAttack), adversarial training, certified robustness, model robustness evaluation, distribution shift, out-of-distribution detection, backdoor attacks, data poisoning, privacy attacks (membership inference, model extraction), and differential privacy in ML.

Triggers when users need help with convolutional neural network architectures, CNN design patterns, or vision model selection. Activate for questions about ResNet, EfficientNet, ConvNeXt, depthwise separable convolutions, feature pyramid networks, receptive field analysis, normalization layers, Vision Transformers vs CNNs tradeoffs, and transfer learning from pretrained CNNs.

Triggers when users need help with generative deep learning models, image synthesis, or density estimation. Activate for questions about GANs, diffusion models, VAEs, flow-based models, DDPM, StyleGAN, mode collapse, classifier-free guidance, latent diffusion, ELBO, autoregressive generation, and evaluation metrics like FID, IS, and CLIP score.

Triggers when users need help with graph neural networks, graph representation learning, or applying deep learning to graph-structured data. Activate for questions about GCN, GAT, GraphSAGE, message passing, over-smoothing, graph pooling, heterogeneous graphs, temporal graphs, knowledge graphs with GNNs, molecular property prediction, social network analysis, recommendation systems on graphs, and GNN scalability.

Triggers when users need help with multimodal deep learning, vision-language models, or cross-modal representation learning. Activate for questions about CLIP, LLaVA, Flamingo, image captioning, visual question answering, text-to-image alignment, contrastive learning across modalities, audio-visual learning, multimodal fusion strategies (early, late, cross-attention), and multimodal benchmarks.

Triggers when users need help with neural architecture search, automated model design, or model compression. Activate for questions about NAS methods (reinforcement learning, evolutionary, differentiable/DARTS), search spaces, one-shot NAS, hardware-aware NAS, AutoML pipelines, efficient architecture design principles, scaling strategies (width, depth, resolution), and model compression (pruning, quantization, distillation).

Triggers when users need help with recommendation systems, collaborative filtering, or ranking models. Activate for questions about matrix factorization, ALS, content-based filtering, deep recommender models (NCF, Wide&Deep, DeepFM, two-tower), sequential recommendation, cold start problem, implicit vs explicit feedback, multi-objective ranking, exploration vs exploitation, and real-time recommendation serving.

Triggers when users need help with recurrent neural networks, sequence modeling with LSTMs or GRUs, or modern state-space models. Activate for questions about vanishing gradients, sequence-to-sequence models, attention mechanisms in RNNs (Bahdanau, Luong), bidirectional RNNs, Mamba, S4, and when RNNs still outperform transformers for sequential data.

Triggers when users need help with preventing overfitting, improving model generalization, or applying regularization techniques. Activate for questions about dropout, weight decay, data augmentation (CutMix, MixUp, RandAugment, AugMax), label smoothing, early stopping, knowledge distillation, ensemble methods, bias-variance tradeoff in deep learning, and double descent phenomenon.

Triggers when users need help with self-supervised learning, representation learning without labels, or pretext task design. Activate for questions about contrastive learning (SimCLR, MoCo, BYOL), masked modeling (MAE, BEiT, data2vec), pretext tasks, representation evaluation (linear probing, fine-tuning), self-supervised methods for vision vs NLP vs audio, DINO and DINOv2, and curriculum learning.

Triggers when users need help with speech processing, audio machine learning, or sound generation. Activate for questions about ASR architectures (CTC, attention-based, Whisper), text-to-speech (Tacotron, VITS, neural codec models), speaker verification, speaker diarization, audio classification, music generation, speech enhancement, speech separation, mel spectrograms, and audio tokenization (SoundStream, EnCodec).

Triggers when users need help with deep learning training procedures, optimizer selection, or training efficiency. Activate for questions about SGD, Adam, AdamW, LAMB, Lion, learning rate schedules, gradient clipping, mixed precision training, FP16, BF16, gradient accumulation, weight initialization, loss landscape analysis, and hyperparameter tuning including Bayesian optimization and population-based training.