skills.rest
GeneralReasoning
GeneralReasoningOFFICIAL
Explore all skills by this author →
Website𝕏@GenReasoningGitHub

time_series_anomaly_detection

Detect category-level time-series anomalies by comparing Prophet forecasts to actual observations.

4|Updated Feb 22, 2026
Search Tags:#forecasting#time-series#data-analysis#anomaly-detection#category-analysis#prophet
One-click install
npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill time-series-anomaly-detection
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: time_series_anomaly_detection
Source: https://github.com/GeneralReasoning/env-skillsbench/tree/main/trend-anomaly-causal-inference/environment/skills/time_series_anomaly_detection
Command: npx skills add https://github.com/GeneralReasoning/env-skillsbench --skill time-series-anomaly-detection

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, prophet, tqdm, and includes scripts (resource) components.

What problem does it solve?

Detects anomalies in time-series data by comparing actual observations to Prophet-based forecasts, enabling early identification of unusual surges or slumps.

Core Features & Use Cases

  • Prophet-based category-level forecasting across multiple groups
  • Per-category anomaly indexing and structured summaries
  • Use cases include monitoring sales, sensor data, and digital metrics to trigger interventions

Quick Start

Provide your time-series DataFrame with date, category, and value columns, then run detect_anomalies with a cutoff_date and prediction_end to receive anomaly summaries.

Frequently Asked Questions about time_series_anomaly_detection

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

FAQPage Schema
How do I detect time-series anomalies across multiple categories in Python?▼

You need Python, Prophet, pandas, and numpy installed. Configure a cutoff_date and prediction_end, then provide a DataFrame with date, category, and value columns to generate anomaly indices and model summaries.

Can I use Prophet for category-level forecasting on sales or sensor data?▼

It forecasts expected trends per category and measures deviations against actual observations to identify unusual surges or slumps, applicable to multi-category datasets like sales, sensor readings, or web metrics.

What's the best way to monitor time-series data for unexpected surges or slumps?▼

Comparing actual observations to Prophet-based forecasts enables early identification of unusual surges or slumps, generating per-category anomaly indices and structured summaries to trigger interventions.

Does time-series anomaly detection work with multi-category DataFrames?▼

It processes DataFrames containing date, category, and value columns to produce per-category anomaly indexing and structured summaries for multi-category datasets.

What are the limitations of using Prophet for anomaly detection?▼

It requires predefined cutoff_date and prediction_end configurations and a structured DataFrame with date, category, and value columns, relying on Prophet's forecasting capabilities for accurate deviation measurement.

Related Skills

Explore More Data & Analytics Skills→
agentscope-aiagentscope-ai
98

hierarchical-taxonomy-clustering

Generate unified multi-level category taxonomies from hierarchical product paths.

Official
Advanced
Arnutt-NArnutt-N

audit-dashboard

Consolidate real-time HR-IMS audit events into a unified monitoring dashboard.

Community
Advanced
Imad-OuteImad-Oute

aeon

Preprocess, extract features, and model time series data with scikit-learn, pandas, and numpy.

Community
Intermediate
vasilyu1983vasilyu1983
73

ai-ml-timeseries

Forecast time series data with LightGBM, Transformers, and SHAP.

Community
Advanced