Browse Skills

Guides the end-to-end deployment of TensorFlow Lite models on mobile and edge devices — from model conversion and quantization to on-device inference optimization, hardware delegate selection, and production monitoring. Ensures models meet latency, size, and accuracy constraints for resource-constrained environments.

Builds and evaluates demand forecasting systems using statistical time series methods and machine learning, covering decomposition, model selection, accuracy measurement, and translation to inventory and planning decisions.

Expert guidance on real-time stream processing architectures using Apache Kafka, Flink, and Spark Streaming, covering windowing strategies, exactly-once semantics, CEP, and operational best practices.

Designs unified customer profiles using Segment, RudderStack, or custom CDP solutions with identity resolution, event streaming, audience segmentation, and privacy-compliant data governance.

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.

Expert in unsupervised learning techniques — clustering, dimensionality reduction, anomaly detection, and pattern discovery with scikit-learn, UMAP, and HDBSCAN.

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.

Designs comprehensive data labeling strategies including annotation pipeline architecture, inter-annotator agreement measurement, active learning loops, label quality control, crowdsourcing management, few-shot labeling, and weak supervision techniques.

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.

Zero praise. Zero sycophancy. Based on research showing LLMs are 45 percentage points more affirming than humans. Forces honest, unfiltered feedback.

Every technical concept explained through pop culture. Your error handling is Gandalf. Your database is the Death Star. Your refactor is a Thanos snap.

Over-the-top motivational cheerleader. Every line of code is a masterpiece. Uses real Claude-isms from 819 API responses across 7 languages, cranked to 11.

Designs, builds, and validates high-quality training datasets for LoRA fine-tuning of large language models, applying data-centric AI principles and instruction-tuning best practices to maximize model performance per training example.

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.