Browse Skills

Guide systematic exploratory data analysis workflows — from initial profiling through distribution analysis, correlation discovery, and hypothesis generation — using statistical rigor and effective visualization.

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

Designs and executes rigorous causal evaluations of policy interventions using econometric methods like DiD, RDD, and instrumental variables, with OECD and EU regulatory frameworks.

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

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

Expert analytics engineering skill for dbt Core/Cloud — guides you through SQL-based data modeling with staging/intermediate/mart layers, dimensional modeling (Kimball methodology), incremental models, SCD Type 2 snapshots, comprehensive testing strategies, Jinja macros, dbt packages, and warehouse-specific optimization for Snowflake, BigQuery, and Redshift.

Guides you through designing effective, insight-driven dashboards with proper KPI selection, visual encoding, and data storytelling — applying Tufte and Few principles to avoid common anti-patterns.

Guides you through building robust data quality frameworks — from validation rules and schema enforcement to data observability, data contracts, and remediation workflows — using industry tools like Great Expectations and Soda.

Prepare research outputs for public sharing and long-term preservation with FAIR-compliant data packaging, reproducible environments, proper licensing, and repository publication strategies.

Design, analyze, and interpret A/B tests using Bayesian statistical methods. Provides posterior distributions, credible intervals, expected loss calculations, and actionable recommendations for experiment-driven decision making.

Designs multi-stage ML model deployment pipelines with automated rollback triggers, canary releases, and shadow deployments to ensure safe, reversible model updates in production.

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.

Reduces LLM API costs through systematic token optimization — prompt compression, caching strategies, model routing, and batch processing — while maintaining output quality across OpenAI, Anthropic, and open-source models.

Designs measurable outcome indicator frameworks for social impact programs, including theories of change, logic models, SMART indicators, and results-based monitoring systems.

Designs retention measurement systems, builds churn prediction models, and creates data-driven intervention strategies that measurably reduce customer churn across SaaS, e-commerce, and subscription businesses.

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.

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.

Design and build custom, interactive data visualizations using D3.js with proper data binding, responsive layouts, accessible markup, and publication-quality visual encoding.

Rigorous causal inference methods for isolating the true impact of price changes on demand, revenue, and customer behavior using econometric techniques, DAG-based reasoning, and experimentation design.

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

Design domain-oriented, decentralized data architectures using data mesh principles including data-as-a-product, self-serve infrastructure, and federated computational governance.

Create publication-quality static figures with Matplotlib and interactive web-ready visualizations with Plotly, guided by visual perception research and data storytelling principles.

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

Expert analyst for designing and implementing customer segmentation strategies — from RFM analysis, behavioral clustering, and cohort modeling to persona creation, segment sizing, and actionable marketing recommendations based on data-driven customer groupings.