How does the skill handle non-stationary data?

It includes specific guidance on using ADF and KPSS tests to detect non-stationarity, followed by differencing, log transforms, and Box-Cox transformations to prepare the data.

Does it support seasonal data analysis?

Absolutely. It features tools for classical and STL decomposition to isolate seasonal components and provides SARIMA and Prophet configurations specifically for periodic data.

Which forecasting libraries does this skill utilize?

The skill provides implementation patterns for popular Python libraries including Statsmodels, Pmdarima, Prophet, Scikit-learn, and TensorFlow/Keras.

Can this skill help with detecting outliers in time series?

Yes, it provides several strategies for anomaly detection, ranging from statistical Z-scores and IQR methods to machine learning approaches like Isolation Forest.

Time Series Analyst

Name: Time Series Analyst
Author: organvm-iv-taxis

byorganvm-iv-taxis

•

데이터 과학 및 ML

Analyzes and forecasts temporal data using statistical models and machine learning to identify trends, seasonality, and anomalies.

The Time Series Analyst skill provides a comprehensive framework for Claude to handle complex temporal datasets. It guides the user through the entire data science pipeline for time-dependent information, including stationarity testing, decomposition of seasonal components, and the implementation of both classical statistical models like ARIMA/SARIMA and modern machine learning approaches such as Facebook Prophet and LSTMs. Whether you are building financial forecasts, monitoring system health, or predicting consumer demand, this skill offers the specific implementation patterns and evaluation metrics needed to ensure accuracy and reliability in temporal modeling.

주요 기능

01Multi-method anomaly detection including Isolation Forest and rolling statistics

02Automated stationarity testing and data transformation workflows

03Statistical forecasting using ARIMA, SARIMA, and Exponential Smoothing

042 GitHub stars

05Modern ML-based modeling with Facebook Prophet and LSTM networks

06Detailed time series decomposition for trend and seasonality analysis

사용 사례

01Predicting business KPIs and financial market movements

02Implementing real-time anomaly detection for infrastructure monitoring

03Generating seasonal demand forecasts for inventory management

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add organvm-iv-taxis/a-i--skills time-series-analyst

For use in Claude.ai and ChatGPT

주요 기능

01Multi-method anomaly detection including Isolation Forest and rolling statistics

02Automated stationarity testing and data transformation workflows

03Statistical forecasting using ARIMA, SARIMA, and Exponential Smoothing

042 GitHub stars

05Modern ML-based modeling with Facebook Prophet and LSTM networks

06Detailed time series decomposition for trend and seasonality analysis

사용 사례

01Predicting business KPIs and financial market movements

02Implementing real-time anomaly detection for infrastructure monitoring

03Generating seasonal demand forecasts for inventory management

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add organvm-iv-taxis/a-i--skills time-series-analyst

For use in Claude.ai and ChatGPT