Browse Skills

Diagnoses slow queries and delivers specific optimization strategies including execution plan analysis, indexing, partitioning, materialized views, and query rewriting with implementation-ready SQL.

Expert in AI cost optimization — token efficiency, model routing, prompt caching, GPU cost management, and inference optimization strategies for LLMs and ML systems.

Designs AI agent systems including multi-agent orchestration, tool use patterns, memory architectures, planning algorithms (ReAct, Chain-of-Thought), agent safety guardrails, and production-grade agent frameworks.

Expert in multi-agent AI systems — workflow coordination, tool-using agents, human-in-the-loop patterns, agent communication protocols, and production deployment of agent architectures.

Expert in advanced PostgreSQL — performance tuning, query optimization, extensions (PostGIS, pgvector, TimescaleDB), partitioning, replication, and production operations.

Expert in PyTorch production systems — neural network architecture, training loops, CNNs, distributed training, and model optimization for deployment.

Diagnoses and resolves neural network training failures including gradient issues, loss plateaus, overfitting, and suboptimal hyperparameters. Provides systematic debugging workflows with actionable fixes.

Designs and implements enterprise data catalog strategies covering metadata management, data discovery, lineage tracking, tagging taxonomies, and platform selection to make organizational data findable and trustworthy.

Design, structure, and optimize production-grade system prompts for large language models using proven architectural patterns, research-backed techniques, and adversarial testing methodologies.

Optimizes ML model deployment for production inference including quantization (INT8/INT4), knowledge distillation, ONNX/TensorRT conversion, model pruning, batching strategies, and edge deployment for reducing latency and cost.

Expert in Snowflake data platform — data warehousing, Snowpark, data sharing, cost optimization, performance tuning, and modern ELT patterns with dbt.

Expert in Bayesian statistical methods — Bayesian A/B testing, credible intervals, prior selection, hierarchical models, and probabilistic decision-making with PyMC and Stan.

Provides expert guidance on time series forecasting including statistical methods (ARIMA, ETS), Prophet, neural forecasting (N-BEATS, Temporal Fusion Transformer), seasonality decomposition, anomaly detection, and confidence interval estimation.

Builds comprehensive responsible AI frameworks including governance structures, model cards, risk assessment processes, fairness metrics, transparency reporting, and regulatory compliance strategies aligned with the EU AI Act and global standards.

Designs recommendation systems covering collaborative filtering, content-based filtering, hybrid approaches, cold start solutions, embedding models, real-time serving, and A/B testing strategies for personalized user experiences.

Provides expert guidance on statistical methodology — from hypothesis testing and regression to Bayesian methods and experimental design — while actively guarding against common pitfalls like p-hacking and multiple comparison errors.

Architects multimodal AI systems that combine vision, language, and audio modalities. Designs cross-modal fusion strategies, selects appropriate models (CLIP, GPT-4V, Gemini), and builds end-to-end multimodal pipelines.

Expert regression analysis guidance covering model selection, diagnostics, regularization, and causal inference across OLS, GLM, and ML techniques.

Designs and optimizes retrieval-augmented generation systems for customer support operations, including knowledge base ingestion, chunking strategies, hybrid retrieval pipelines, answer generation with citation, and continuous quality improvement loops.

Expert guidance on making machine learning models interpretable and explainable using SHAP, LIME, inherently interpretable models, and regulatory-compliant explanation strategies for high-stakes AI systems.

Architect production-grade AI applications with prompt chaining, agent patterns, guardrails, cost optimization, and multimodal capabilities for reliable LLM-powered systems.

Designs reverse ETL architectures to activate warehouse data in operational tools, covering Census/Hightouch patterns, sync strategies, audience building, and data activation use cases.

Designs and optimizes vector embedding systems for semantic search, similarity matching, and retrieval applications. Covers embedding model selection, dimensionality reduction, vector database architecture, and search quality optimization.

Design reliable structured data extraction and generation systems powered by LLMs, with JSON Schema design, provider-specific configuration, validation pipelines, and production error handling.