Advanced AgentDB projects need reliable patterns for sync, search, and database operations. This skill gives practical guidance for QUIC sync, hybrid search, sharding, and production tuning.

Distributed vector search needs careful replication, metrics, monitoring, and deployment planning. This skill gives a phased AgentDB workflow for scalable hybrid search systems.

Analytics events often drift from schema, PII, and registration standards. This skill guides MixPanel implementation and review for Django optimo_analytics workflows.

Manual arithmetic checks slow agents when users need quick numeric answers. This skill evaluates basic math expressions and returns concise results.

Database users need reliable SQL that matches their connection type and schema. This skill guides Claude, Codex, and Claude Code to inspect schemas, write read-only queries, and explain results clearly.

Writing correct SQL across database dialects is slow and error-prone. This skill helps Claude, Codex, and Claude Code create safe DBX Studio queries.

Turning raw query results into the right chart can take repeated setup. This skill guides Claude, Codex, and Claude Code to choose chart types, write SELECT queries, and call DBX Studio chart generation.

Database teams often need a quick view of tables, relationships, and data quality before analysis. This skill guides Claude, Codex, or Claude Code through a structured DBX Studio profiling workflow.

Exploring an unfamiliar database can be slow and inconsistent. This skill gives DBX Studio a repeatable workflow for schema review, profiling, relationships, and quality checks.

Finding purchasable compounds and docking-ready structures in ZINC can require complex queries. This skill guides searches, downloads, filtering, and result interpretation through documented ZINC services.

Large scientific arrays can overwhelm memory and make cloud storage inefficient. This skill guides chunking, compression, storage backends, parallel access, and ecosystem integrations with Zarr-Python.

High-dimensional datasets are difficult to visualize and cluster effectively. This skill provides practical UMAP workflows, parameter guidance, and integration patterns.

Graph learning projects require specialized data structures, layers, sampling, and evaluation workflows. This skill provides PyTorch Geometric guidance, references, templates, visualization, and benchmarking utilities.

Selecting and validating statistical models requires careful choices about outcomes, assumptions, diagnostics, and interpretation. This skill provides Statsmodels workflows for regression, time series, testing, forecasting, and robust inference.

Choosing tests and reporting results correctly requires careful assumptions, diagnostics, and interpretation. This skill provides structured guidance, Python examples, automated checks, and APA-style reporting templates.

Complex queues and shared resources are difficult to evaluate before deployment. This skill guides SimPy models, monitoring, synchronization, and result analysis.

Machine learning teams need clear reasons for model predictions and feature influence. This skill provides SHAP workflows, explainer selection, plots, and interpretation guidance for common model types.

Production ML systems are hard to design, deploy, monitor, and improve reliably. This skill gives Claude, Codex, and Claude Code structured ML engineering guidance.

Choosing appropriate statistical plots and settings can be difficult when datasets contain multiple variable types and groups. This skill guides Seaborn plot selection, composition, styling, and troubleshooting.

Single-cell analyses require careful model and workflow choices across diverse modalities. This skill provides scvi-tools guidance for preprocessing, model selection, training, integration, and interpretation.