Iot Anomalies

This runs Z-score anomaly detection on Cognitum Seed device telemetry and classifies what it finds into six types: spikes, flatlines, drift, oscillation, pattern breaks, and cluster outliers. You pass in a device ID and it pulls recent data, scores the anomalies, and can flag devices for quarantine if the score breaks 0.9. It also stores patterns to memory so Claude can learn from past incidents. Useful if you're managing IoT fleets and need to catch hardware failures or sensor drift before they cascade. The detection happens through an npx package, so nothing to install permanently.

skills.sh installs: 731
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill iot-anomalies --agent claude-code

Installs into .claude/skills of the current project.

Files

Run Z-score anomaly detection on a device's recent telemetry.

Steps:

npx -y -p @claude-flow/plugin-iot-cognitum@1.0.0 cognitum-iot anomalies DEVICE_ID
Review detected anomaly types (spike, flatline, drift, oscillation, pattern-break, cluster-outlier)
If score > 0.9, recommend quarantine
Store anomaly pattern for learning: mcp__plugin_ruflo-core_ruflo__memory_store({ key: "iot-anomaly-DEVICEID", value: "TYPE at SCORE", namespace: "iot-anomalies" })

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly