skills.rest
bettercallfan
bettercallfanCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

detect_flow_anomaly

Detect macro-level mobility flow anomalies in spatiotemporal JSONL data.

Updated Jun 2, 2026
Search Tags:#anomaly detection#geohash#spatiotemporal analysis#mobility flow#flow analytics
One-click install
npx skills add https://github.com/bettercallfan/deerflow --skill detect-flow-anomaly
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: detect_flow_anomaly
Source: https://github.com/bettercallfan/deerflow/tree/main/skills/custom/spatiotemporal_trajectory/detect_flow_anomaly
Command: npx skills add https://github.com/bettercallfan/deerflow --skill detect-flow-anomaly

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill identifies anomalies in mobility flow data, such as abnormal regional heat, check-in spikes, OD flow spikes, sudden decreases, or unusual activity patterns in specific time windows.

Core Features & Use Cases

  • Detect Anomalies: Identifies anomalies like abnormal regional heat or OD flow spikes in mobility data.
  • Data Formats: Processes data in JSONL format containing region heat or OD flow data.
  • Use Case: For instance, after analyzing network traffic or travel patterns, use this skill to identify unusual traffic spikes or check-in patterns during off-peak hours.

Quick Start

To detect anomalies in mobility flow data, use the detect_flow_anomaly skill with the command:

detect_flow_anomaly --input path/to/region_heat.jsonl --output-dir path/to/output

Frequently Asked Questions about detect_flow_anomaly

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

FAQPage Schema
How do I detect mobility flow anomalies in spatiotemporal data?▼

To detect mobility flow anomalies, process your spatiotemporal data in JSONL format with specified group and metric columns. This identifies abnormal regional heat, check-in spikes, and OD flow spikes.

What types of spatiotemporal anomalies can I identify in mobility flow data?▼

Spatiotemporal anomaly detection identifies abnormal regional heat, check-in spikes, OD flow spikes, sudden decreases, and unusual activity patterns within specific time windows of mobility flow data.

How do I find abnormal OD flow spikes using geohash data?▼

Finding abnormal OD flow spikes requires inputting JSONL formatted data containing specified group and metric columns. The analysis detects macro-level mobility flow anomalies like regional heat and check-in spikes.

Can I use JSONL files to detect sudden decreases in regional heat?▼

Yes, JSONL files containing region heat or OD flow data with specified group and metric columns are required. The analysis detects sudden decreases and unusual time-window activity in spatiotemporal data.

What is the best way to identify unusual check-in spikes during off-peak hours?▼

The best way to identify unusual check-in spikes during off-peak hours is running anomaly detection on spatiotemporal mobility data. Provide JSONL input with specified group and metric columns for analysis.

Do I need specific columns to analyze spatiotemporal anomalies in mobility flow?▼

Yes, you need specified group and metric columns in your JSONL input data to analyze spatiotemporal anomalies. These columns enable the detection of macro-level mobility flow anomalies like OD flow spikes.

Related Skills

Explore More Data & Analytics Skills→
bettercallfanbettercallfan

measure_spatiotemporal_entropy

Calculate spatiotemporal entropy and vitality index from OD matrices and evidence records.

Community
Intermediate
bettercallfanbettercallfan

analyze_spatiotemporal_accessibility

Computes empirical isochrones and reachable areas from OD matrix and starting geohash.

Community
Intermediate
bettercallfanbettercallfan

clean_trajectory

Validate and clean GPS trajectory files with geohash encoding.

Community
Intermediate
anton-abyzovanton-abyzov
156

anomaly-detector

Detect anomalies and outliers using statistical methods, Isolation Forest, and autoencoders.

Community
Advanced