Browse Skills

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

Designs privacy-preserving distributed machine learning systems using federated learning. Covers federated averaging, differential privacy, secure aggregation, communication efficiency, and compliance with privacy regulations.

Expert in AI safety evaluation — adversarial testing, jailbreak prevention, prompt injection defense, bias detection, and safety benchmarking for LLMs and AI systems.

Design and implement retrieval-augmented generation systems for legal documents with citation-safe retrieval, hallucination prevention, and privilege-aware document handling.

Designs optimal text chunking strategies for Retrieval-Augmented Generation (RAG) systems, balancing chunk size, semantic coherence, retrieval precision, and generation quality across diverse document types.

Evidence-based framework that classifies AI-assisted coding practices into High-Leverage, Context-Dependent, and Dangerous tiers with a rigorous 4-criteria evaluation rubric.

Develops comprehensive data governance strategies including data catalogs, metadata management, ownership models, access policies, quality frameworks, and master data management aligned with DMBOK standards.

Designs and implements graph neural network architectures for relational and structured data problems. Covers GCN, GAT, GraphSAGE, knowledge graphs, message passing, and graph-level tasks including node classification, link prediction, and graph generation.

Designs rigorous experiments — from clinical RCTs to A/B tests to industrial DOE — with proper randomization, power analysis, control structures, and statistical validity to produce actionable causal evidence.

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

Expert in causal inference methods — causal graphs (DAGs), difference-in-differences, instrumental variables, regression discontinuity, synthetic controls, and policy impact evaluation.

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

Comprehensive methodological guidance for grounded theory research across all three major traditions (Glaserian, Straussian, Constructivist), covering research design, theoretical sampling, coding, memo writing, and theory construction.

Evaluates machine learning models with rigorous methodology and statistical analysis. Covers metrics selection, cross-validation strategies, bias detection, A/B testing, confusion matrices, ROC/AUC analysis, and comprehensive evaluation reporting.

Advanced Claude Code orchestration covering subagent strategies, hook engineering, permission architecture, context economy, headless CI pipelines, and session management for power users.

Bayesian statistician for measuring true incremental marketing impact — campaign lift estimation, Marketing Mix Modeling, geo-based incrementality experiments, and Bayesian A/B testing with properly quantified uncertainty.

Analyze and optimize Snowflake data warehouse costs through warehouse right-sizing, query performance tuning, storage efficiency, and organizational governance using resource monitors and FinOps practices.

Design synthetic data generation pipelines that produce privacy-preserving, statistically faithful datasets for ML training, testing, and data sharing using GANs, copulas, and differential privacy.

Design and calibrate risk scoring systems that identify at-risk individuals within cohorts — enabling early interventions for student retention, customer churn prevention, patient readmission, and other predictive analytics use cases.

Design and implement safety, quality, and compliance guardrail systems for LLM-powered applications, covering input validation, output screening, prompt injection defense, PII protection, and regulatory compliance mapping.

Designs, builds, and optimizes complex multi-step Zapier workflows connecting multiple SaaS applications, with branching logic, error handling, sub-Zaps, and task optimization for production-grade business automation.

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.

Design BI architectures with semantic layers, dimensional models, self-service analytics, KPI frameworks, and modern data stack patterns using dbt, Looker, Metabase, and Tableau.

Design and implement cohort analyses for retention measurement, behavioral segmentation, and product analytics. Provides SQL implementations, visualization recommendations, and statistical interpretation guidance.