Browse Skills

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.

Design and optimize production-grade NLP pipelines covering text preprocessing, tokenization, NER, sentiment analysis, and transformer-based architectures using spaCy and HuggingFace.

Designs production-grade drift monitoring pipelines for ML models, covering data drift, concept drift, and prediction drift detection with statistical methods, alerting thresholds, and automated response procedures.

Maps end-to-end data lineage from source systems through transformations to downstream consumers, enabling impact analysis, debugging data quality issues, and ensuring regulatory compliance.

Expert guidance for building production-grade LLM applications with LangChain. Covers chain composition with LCEL, RAG pipelines, agent systems, LangGraph workflows, prompt engineering, and production deployment with LangSmith observability.

Design, implement, and operate real-time event streaming systems using Redis Streams. Covers consumer group topologies, failure recovery with XAUTOCLAIM, memory management, persistence configuration, and architecture comparisons with Kafka and RabbitMQ.

Helps you set up and optimize MLflow for experiment tracking, run comparison, model registry management, and production MLOps workflows across any ML framework.

Helps users critically evaluate AI-generated health information, identify hallucinations and red flags, structure medical queries safely, and know when to seek professional care instead of trusting chatbot output.

Design and optimize MongoDB aggregation pipelines for complex data transformations, analytics, and reporting. Covers pipeline stage ordering, index utilization, sharded cluster considerations, and schema design patterns that enable efficient aggregation.

Optimize BigQuery deployments for maximum performance and minimum cost through partitioning, clustering, query tuning, and systematic cost control strategies.

Expert guidance for creating compelling geospatial visualizations and spatial data analysis. Covers map design, PostGIS spatial queries, web mapping libraries (Mapbox, Deck.gl, Leaflet), data formats, and location intelligence.

Helps developers and organizations design safe, compliant AI systems for health-adjacent applications. Covers RAG pipeline architecture, escalation trigger design, disclaimer systems, uncertainty quantification, and regulatory compliance (EU AI Act, FDA, MDR).

Designs comprehensive evaluation frameworks for LLM and AI systems, combining automated metrics (BLEU, ROUGE, BERTScore), LLM-as-judge patterns (G-Eval), RAG evaluation (RAGAS), standard benchmarks (MMLU, HumanEval), safety evaluations, and A/B testing methodologies into production-ready evaluation pipelines.

Guide practitioners through selecting, designing, and interpreting statistical hypothesis tests with proper assumptions checking, sample size calculations, and actionable conclusions.

Systematic research methodology for LLM-assisted workflows. Transforms vague questions into structured inquiry plans using query decomposition, multi-pass retrieval, evidence synthesis, and PRISMA-inspired reporting.

Designs robust ETL and ELT data pipelines with focus on idempotency, incremental loading, data lineage, and orchestration. Guides implementation with Apache Airflow, dbt, and modern data stack tools.

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

Helps users understand the risks of using AI for romantic relationship advice, recognize validation loops and one-sided framing, detect when AI replaces rather than supports human connection, and know when to consult a couples therapist.

Helps parents evaluate AI-generated parenting advice for developmental accuracy, recognize when AI oversimplifies child health decisions, understand cultural bias in AI parenting norms, and know when to consult pediatricians or child psychologists.

Helps users evaluate AI-generated nutrition advice for safety risks, recognize dangerous diet recommendations, identify eating disorder triggers in AI output, and know when to consult a registered dietitian.

Evaluates source credibility, detects fabricated citations, and assesses claim reliability using SIFT, CRAAP, and domain-specific evidence hierarchies. Essential for verifying LLM output and research findings.

Guides decisions on when and how to fine-tune large language models, covering LoRA/QLoRA, dataset curation, RLHF/DPO alignment, evaluation strategies, and cost-performance tradeoffs for production deployments.

Comprehensive guide to designing AI-powered products covering UX patterns, trust and transparency, error handling, feedback loops, ethical considerations, and user research for AI features.

Expert guidance for building and optimizing Apache Spark data processing pipelines, from PySpark development to cluster tuning and lakehouse architecture.