Data & Analytics

Use when implementing causal inference methods in ML.

**Trigger**: Use when working with Google Cloud Bigquery Bigframes — setup, configuration, and best practices. BigFrames is a Python library that lets you take advantage of BigQuery data processing by using familiar Python APIs.

**Trigger**: Use when working with Google BigQuery — querying, partitioning, clustering, cost controls, and best practices. BigQuery is a serverless, AI-ready data platform that enables high-speed analysis of large datasets using SQL and Python. Its disaggregated architecture separates compute and storage, allowing them to scale independently while providing built-in machine learning, geospatial analysis, and business intelligence capabilities.

Use when implementing ML-based anomaly detection systems.

Query Stats NZ DataInfo+ / Aria classifications, concepts, concordances, and quality standards with lookup IDs, code lists, version history, and category metadata.

Discover and fetch Reserve Bank of New Zealand public statistics datasets through data.govt.nz CKAN and browser-compatible rbnz.govt.nz public file/chart endpoints. Use when the task involves RBNZ exchange rates, wholesale interest rates, OCR/key graphs, retail mortgage/deposit rate charts, dataset metadata, resource URLs, downloadable XLSX series, or JSON chart-cache previews. Read-only; no authentication required.

Query New Zealand public and social housing open data from the Ministry of Housing and Urban Development (HUD) on data.govt.nz — public housing stock (Kainga Ora and community housing providers), social housing IRRS and market-rent tenancies, accommodation supplement recipients and weekly spend, and the Local Housing Statistics dashboard (housing affordability, rent burden, bonds, building consents, MSD benefit numbers, and the year-on-year change in the public/social housing register). Use w...

Query Ombudsman NZ OIA/LGOIMA complaint statistics, case notes, and inspection publications from ombudsman.parliament.nz.

Query NZTA/Waka Kotahi Crash Analysis System public crash statistics from the no-key ArcGIS FeatureServer and data.govt.nz CKAN mirror. Use when the task involves New Zealand road deaths, serious injuries, crash severity by region or TLA, yearly road-toll counts, or public CAS crash indicator fields such as weather, light, road surface, vehicle type, roadside objects, and roadworks.

Query official anonymised New Zealand Police victimisation, proceedings and offence statistics with suppression and interpretation context.

Discover New Zealand public procurement opportunities and award notices from GETS, MBIE open-data metadata, and procurement.govt.nz significant-service-contract sources. Use when Codex needs keyless NZ government tender searches, current GETS notices, RFx detail by ID, recent completed/award notices, procurement source URLs, or significant service contract dashboard summaries.

Query official Fire and Emergency New Zealand operational reports and annual incident datasets by place, type and period.

Query New Zealand energy-hardship evidence from MBIE energy-hardship measure reports, Stats NZ Household Expenditure Statistics household energy and electricity expenditure tables, and Electricity Authority disconnection dashboard/source metadata. Use for NZ energy poverty, electricity affordability, domestic-energy burden, 2M or 10 percent hardship proxy research, HES energy expenditure, MBIE five hardship measures, and disconnections for non-payment caveats.

Query official New Zealand child poverty statistics from Stats NZ — the nine Child Poverty Reduction Act measures (BHC/AHC low-income lines, material hardship, severe material hardship, DEP-17 deprivation), national rates and child numbers 2007-2025 with confidence intervals, and breakdowns by region, ethnicity (Māori, Pacific, European, Asian) and disability. Use for tasks about NZ child poverty rates, kids in hardship or deprivation, poverty by region or ethnic group, annual change, or find...

Build best-in-class, real-data-grounded visualizations of YURI's own systems — energy/ΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math / quantum / graph / telemetry data, build a 3D / WebGL / three.js / react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, ...

Build best-in-class, real-data-grounded visualizations of YURI's own systems — energy/ΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math / quantum / graph / telemetry data, build a 3D / WebGL / three.js / react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, ...

Detect DNS tunneling and data exfiltration by analyzing Zeek dns.log for high-entropy subdomain queries, excessive query volume, long query lengths, and unusual DNS record types indicating covert channel communication.

Identify command-and-control beaconing patterns in network traffic by applying statistical frequency analysis, jitter calculation, and coefficient of variation scoring to detect periodic callbacks from compromised endpoints.

Deploy AI and NLP-powered detection systems to identify business email compromise attacks by analyzing writing style, behavioral patterns, and contextual anomalies that evade traditional rule-based filters.

Performs statistical analysis of Zeek conn.log connection intervals to detect C2 beaconing patterns. Uses the ZAT library to load Zeek logs into Pandas DataFrames, calculates inter-arrival time standard deviation, and flags periodic connections with low jitter. Use when hunting for command-and-control callbacks in network data.

Detects anomalous authentication patterns using UEBA analytics, statistical baselines, and machine learning models to identify impossible travel, credential stuffing, brute force, password spraying, and compromised account behaviors across authentication logs. Activates for requests involving authentication anomaly detection, login behavior analysis, UEBA implementation, or suspicious sign-in inve

This skill covers deploying anomaly detection systems for industrial control environments using machine learning models trained on OT network baselines, physics-based process models, and behavioral analysis of industrial protocol communications. It addresses building normal behavior profiles for SCADA polling patterns, detecting deviations in Modbus/DNP3/OPC UA traffic, identifying rogue devices,

Correlates disparate security incidents, IOCs, and adversary behaviors across time and organizations to identify unified threat campaigns, attribute them to common threat actors, and extract shared indicators for improved detection. Use when multiple incidents exhibit overlapping indicators, when sector-wide attack campaigns require cross-organizational analysis, or when building campaign-level in

Build best-in-class, real-data-grounded visualizations of YURI's own systems — energy/ΔU surfaces, quantum Q-spheres, circuitry graphs (2D edge-bundling + 3D die), telemetry cockpits, embedding atlases. Use when the task is to visualize, depict, render, or make interactive any YURI math / quantum / graph / telemetry data, build a 3D / WebGL / three.js / react-three-fiber or D3 visualization, turn a flat view into 3D, or prototype a viz before wiring it into the app. Triggers: visualize, viz, ...