Data & Analytics

Extract dominant colors from images, generate color palettes, and export as CSS, JSON, or ASE with K-means clustering.

Processes Coles grocery invoices to extract structured data and predict future orders. Use when user uploads/pastes invoice content, asks to analyze grocery purchases, or wants shopping predictions.

Semantic code search using Phase 1 vector embeddings and Phase 2 hybrid search.

Calculate and track CO2 emissions and carbon footprint for construction projects.

End-to-end copy number variant detection workflow from BAM files. Covers CNVkit analysis for exome/targeted sequencing with visualization and annotation. Use when detecting copy number alterations from sequencing data.

Identify groups and patterns in data using k-means, hierarchical clustering, and DBSCAN for cluster discovery, customer segmentation, and unsupervised learning

Neural network training and deployment in Flow Nexus cloud. Use for distributed ML training, model inference, and neural network lifecycle management.

Matches patient profiles to open clinical trials using vector similarity and inclusion/exclusion criteria. Use when a user provides patient data and asks for relevant trials.

Run ClickHouse queries for analytics, metrics analysis, and event data exploration. Use when you need to query ClickHouse directly, analyze metrics, check event tracking data, or test query performance. Read-only by default.

Expert assistant for conducting remote experiments with Claude-Light - a web-accessible RGB LED and spectral sensor instrument for statistics, regression, optimization, and design of experiments

Analyze live weather station integrations, validate data sources, and identify spots missing live conditions

Эксперт categorical encoding. Используй для ML feature engineering, one-hot, target encoding и embeddings.

Track blog post performance and generate insights for continuous improvement. USE WHEN user says 'track post performance', 'analyze blog metrics', 'what posts performed well', 'blog analytics', OR requests performance feedback on content.

End-to-end biomarker discovery workflow from expression data to validated biomarker panels. Covers feature selection with Boruta/LASSO, classifier training with nested CV, and SHAP interpretation. Use when building and validating diagnostic or prognostic biomarker signatures from omics data.

Aggregates and analyzes historical data from multiple BigQuery tables with similar schemas. Queries multiple tables using UNION ALL, calculates aggregate metrics (averages, sums, counts), handles table discovery via INFORMATION_SCHEMA, and processes large datasets efficiently with batch queries.

The core skill for working within the bigquery-etl repository. Use this skill when understanding project structure, conventions, and common patterns. Works with model-requirements, query-writer, metadata-manager, sql-test-generator, and bigconfig-generator skills.

Hopf bifurcation detection for dynamical system state transitions with GF(3) phase portraits

Generate bifurcation diagrams for dynamical systems. Use when visualizing parameter-dependent behavior transitions.

Evaluate AI systems for fairness using demographic parity, equalized odds, and bias detection techniques with mitigation strategies.

Details the core betting strategy, including edge calculation, sport-specific thresholds, Kelly Criterion sizing, and portfolio optimization.

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

分析銀行貸款與存款之間的「信貸創造脫鉤」現象，追蹤存款的絕對收縮與回升軌跡，用以辨識聯準會緊縮政策在銀行體系內部的真實傳導效果。

用公開市場數據檢查「利率波動率（MOVE）是否對利率事件（如 JGB 殖利率變動）不恐慌，並且是否領先帶動 VIX / 信用利差走低」。

從日本保險公司對超長期（10年以上）JGB 的淨買賣時間序列，自動產出「本月是否創紀錄淨賣出、連續淨賣出月數、期間累積淨賣出」等結論。