Browse Skills

Design comprehensive evaluation systems for LLMs and AI applications, covering automated metrics, human evaluation protocols, LLM-as-a-judge pipelines, and CI/CD-integrated regression testing.

Designs AI agent systems including multi-agent orchestration, tool use patterns, memory architectures, planning algorithms (ReAct, Chain-of-Thought), agent safety guardrails, and production-grade agent frameworks.

Design and implement machine learning-based lead scoring systems that predict conversion probability, prioritize sales efforts, and automate lead qualification using behavioral, firmographic, and engagement data from CRM platforms.

Design effective chain-of-thought prompting strategies that elicit step-by-step reasoning from large language models for complex problem-solving, analysis, and decision-making tasks.

Optimizes few-shot prompting strategies for large language models by selecting, ordering, and formatting demonstration examples that maximize output quality while minimizing token usage and cost.

Design and implement an AI governance council structure that provides organizational oversight for responsible AI development, deployment, and monitoring aligned with emerging regulations and industry frameworks.

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

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

Designs pedagogically sound automated feedback systems for programming education. Creates error taxonomies, scaffolded hint systems, and feedback message architectures that transform coding errors into effective learning opportunities.

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

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

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

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.

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.

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

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 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 time series forecasting including statistical methods (ARIMA, ETS), Prophet, neural forecasting (N-BEATS, Temporal Fusion Transformer), seasonality decomposition, anomaly detection, and confidence interval estimation.

Builds comprehensive responsible AI frameworks including governance structures, model cards, risk assessment processes, fairness metrics, transparency reporting, and regulatory compliance strategies aligned with the EU AI Act and global standards.

Designs and optimizes retrieval-augmented generation systems for customer support operations, including knowledge base ingestion, chunking strategies, hybrid retrieval pipelines, answer generation with citation, and continuous quality improvement loops.

Performance tuning for Pinecone, Weaviate, Qdrant, and pgvector including index selection, embedding dimensionality, chunking strategies, and hybrid search optimization for RAG systems.

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