mcpField
I
iot-anomalies

iot-anomalies

github.com/ruvnetData & databases80.0k730 installsUpdated today
Repository

About iot-anomalies

A skill that runs Z-score anomaly detection on a device’s recent telemetry and reviews the detected pattern. It can recommend quarantine for high-scoring anomalies and store patterns for learning.

Key features

  1. 01Run Z-score detection on telemetry
  2. 02Review six anomaly types
  3. 03Recommend quarantine above a score threshold
  4. 04Store anomaly patterns

Use cases

  1. 01Check a device’s recent telemetry for anomalies
  2. 02Review spikes, drift, or pattern breaks
  3. 03Save anomaly patterns for later learning

MCP support

Uses the Ruflo memory store tool to save detected anomaly type and score in the iot-anomalies namespace.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill iot-anomalies

After installing, type/iot-anomaliesin Claude Code to confirm it loaded.

Details

From the project README

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

Steps:

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

Comments

Markdown supported