Identify anomalies in geometric data spheres via targeted scans.
npx skills add https://github.com/hypertopos/hypertopos-skills --skill gds-analyst
Please help me install this Agent Skill. Skill: gds-analyst Source: https://github.com/hypertopos/hypertopos-skills/tree/main/gds-analyst Command: npx skills add https://github.com/hypertopos/hypertopos-skills --skill gds-analyst
GDS anomaly investigation provides a goal-oriented framework that transforms hints about a sphere into concrete, actionable investigation steps, surfacing anomalies and actionable findings rather than raw observations.
Describe a sphere hint and let gds-analyst select and execute the appropriate scans to surface findings.
High-intent search queries and answers about installing and using this skill.
Anomaly investigation in trajectory data works by applying cross-pattern profiling and temporal drift analyses to geometric data spheres. You can start from a simple sphere hint, and the system orchestrates targeted scans to surface actionable findings without requiring explicit anomaly categories.
Root-cause analysis for geometric data spheres explores multi-pattern reasoning to identify contributing factors and counterparty relationships. It transforms hints about a sphere into concrete investigation steps, surfacing actionable findings rather than raw observations.
Targeted scans for temporal drift in geometric data are orchestrated automatically based on your sphere hint. The system selects and executes appropriate scans including neighbor, segment, and trajectory analyses to detect temporal changes and surface anomalies.
Geometric data sphere investigation ensures compatibility with Claude Code-compatible agents and the hypertopos MCP server. You can apply it to any sphere investigation scenario using live or static data, orchestrating scans through compatible agent environments.
Starting an anomaly investigation from a sphere hint involves describing the hint and letting the system select the appropriate scans. It automatically orchestrates cross-pattern, neighbor, trajectory, and temporal analyses to surface actionable findings.
Geometric data anomaly investigation is adaptable to both live and static data. It supports any investigation task on geometric data spaces, applying trajectory detection and cross-pattern profiling to surface anomalies regardless of data state.
hypertoposMonitor GDS sphere health and detect temporal drift and regime changes.
LitheScriptDiagnose cascading failure root causes using logs, metrics, and traces.
hypertoposDetect multi-pattern anomalies in geometric data spaces using GDS detection recipes.
nrakowAutomate anomaly detection in dbt data pipelines for volume, freshness, and distribution issues.
