Browse Skills

Design rigorous A/B experiments, calculate sample sizes, select statistical methods, analyze results with proper significance testing, and deliver actionable recommendations.

Guides analytics engineering best practices using dbt, SQL modeling patterns, semantic layers, metrics definitions, and testing strategies. Helps design maintainable, well-documented analytics workflows from raw data to business-ready datasets.

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

Designs and implements enterprise skills taxonomies and competency frameworks that enable skills-based workforce planning, internal mobility, gap analysis, and learning path mapping using validated I/O psychology methodologies.

Helps users understand why real legal advice is structurally impossible for LLMs, evaluate AI-generated legal content for hallucinated cases and fabricated citations, and know when to consult a licensed attorney.

Design and implement MLOps platforms covering model serving, feature stores, CI/CD for ML, model monitoring, drift detection, A/B testing, and GPU resource management.

Design and build reliable API integrations in Make (formerly Integromat) using HTTP modules, OAuth flows, pagination handling, and advanced error recovery patterns.

Build, evaluate, and deploy machine learning models directly in Google BigQuery using SQL, from classification and regression to time-series forecasting and recommendations.

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.

Helps older adults (60+) and their families understand AI tools safely, recognize health information risks amplified by low digital literacy, protect against AI-enabled scams, and use AI companions responsibly.

Design dimensional models, data vault architectures, and analytics schemas optimized for Snowflake with Kimball methodology, dbt integration, and platform-native performance tuning.

Design optimal database indexing strategies by analyzing query patterns, understanding index internals, and balancing read performance against write overhead for PostgreSQL, MySQL, and other relational databases.

Analyzes conversion funnels across acquisition, activation, and monetization stages, identifying drop-off points, statistical significance of changes, and optimization opportunities using event data.

Design, optimize, and operate ClickHouse OLAP clusters for real-time analytics on billions of rows with sub-second query performance.

Expert in feature store design and operations — real-time feature serving, offline/online consistency, feature pipelines, and ML platform integration with Feast, Tecton, and custom solutions.

Design rigorous geographic experiments (geo-lift tests) to measure the true incremental impact of marketing campaigns, product launches, and pricing changes using causal inference methods.

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 intelligent model routing systems that optimize cost, latency, and quality across multiple LLM providers. Covers cascading strategies, confidence-based escalation, prompt caching economics, and fallback architectures.

Expert in Python-based data analysis — Pandas, NumPy, exploratory data analysis, statistical profiling, data cleaning, and visualization for business insights.

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).

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 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.

Designs end-to-end computer vision pipelines including model selection (CNN/ViT/YOLO), data augmentation, training strategies, transfer learning, and production deployment with ONNX/TensorRT optimization for cloud and edge.

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.