gds-detective

Name: gds-detective
Availability: InStock
Author: hypertopos

Detect multi-pattern anomalies in geometric data spaces using GDS detection recipes.

Updated Apr 9, 2026

Search Tags:#patterns #drift #anomaly-detection #burst #gds #cross-pattern

Ready to run

npx skills add https://github.com/hypertopos/hypertopos-skills --skill gds-detective

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gds-detective
Source: https://github.com/hypertopos/hypertopos-skills/tree/main/gds-detective
Command: npx skills add https://github.com/hypertopos/hypertopos-skills --skill gds-detective

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Detect anomalies in geometric data spaces by applying structured detection recipes that surface multi-pattern signals beyond single-feature profiling, enabling faster root cause understanding and robust alerting.

Core Features & Use Cases

Event anomaly rate recipes to surface joint deviations across patterns
Composite subgroup analysis to catch Simpson's paradox
Temporal burst detection, trajectory and drift analyses, and cross-pattern investigations
Passive_scan for confirmation and multi-pattern risk assessment
Use Case: surfaces anomalies in sphere data and supplier networks to trigger investigations.

Quick Start

Invoke gds-detective on your current sphere to run detection recipes and surface cross-pattern anomalies.

Frequently Asked Questions about gds-detective

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect multi-pattern anomalies in geometric data spaces?▼

Detect temporal bursts and drift in geometric data by applying structured detection recipes that analyze trajectory shapes and temporal shifts. These recipes surface multi-pattern signals to trigger cross-pattern investigations and robust alerting.

What is the best way to investigate cross-pattern anomalies and neighbor contamination?▼

Catch Simpson's paradox using composite subgroup analysis recipes that evaluate joint deviations across patterns. These recipes surface composite anomalies in sphere data and supplier networks that single-feature profiling misses.

Do I need a specific MCP server to run GDS detection recipes?▼

Run sphere_overview alerts by invoking gds-detective on your current sphere to execute detection recipes. This surfaces cross-pattern anomalies, segment shifts, and trajectory shapes to trigger end-to-end investigation workflows.

How do I identify temporal bursts and drift in sphere data?▼

Identify temporal bursts and drift in sphere data by applying structured GDS detection recipes for trajectory analysis and temporal shifts. These recipes surface multi-pattern signals that trigger robust alerting and cross-pattern investigations.

Can I use composite subgroup analysis to catch Simpson's paradox in supplier networks?▼

Use composite subgroup analysis recipes to catch Simpson's paradox by evaluating joint deviations across patterns in supplier networks. This surfaces composite anomalies that single-feature profiling misses, enabling faster root cause understanding.