000-docs/000a-planned-skills/core-forecasting/nixtla-exogenous-integrator/SKILL.md
Incorporates external variables (holidays, weather, events) into TimeGPT forecasts to improve accuracy. Use when forecasts require external data, holidays impact sales, or weather affects demand. Trigger with "include holidays", "add weather data", "integrate events".
npx skillsauth add intent-solutions-io/plugins-nixtla nixtla-exogenous-integratorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Augments TimeGPT forecasts with exogenous variables for increased accuracy.
Enhances time series predictions by integrating external data sources like holidays, weather, and events.
This skill enriches TimeGPT forecasts by considering external factors influencing time series data. It reads exogenous data from CSV files, aligns it with the historical data, and passes both to the TimeGPT API. This integration improves forecast accuracy, especially when events or external conditions affect the time series. The skill outputs an augmented forecast incorporating the impact of these exogenous variables.
Tools: Read, Write, Bash, Glob, Grep
Environment: NIXTLA_TIMEGPT_API_KEY
Packages:
pip install nixtla pandas matplotlib
Read historical time series CSV and exogenous variables CSVs. Ensure they have a common date ('ds') column.
Script: {baseDir}/scripts/load_data.py
Usage:
python {baseDir}/scripts/load_data.py data.csv holidays.csv
The loader expects:
unique_id, ds, y columnsds column plus feature columnsMerge historical and exogenous dataframes based on the 'ds' column using the alignment script.
Script: {baseDir}/scripts/align_data.py
The script validates that both datasets share a 'ds' column and checks for column name conflicts. It performs a left join to preserve all historical timestamps.
Run the integration script with your data files and forecast parameters.
Script: {baseDir}/scripts/integrate_exogenous.py
Usage:
python {baseDir}/scripts/integrate_exogenous.py \
--input data.csv \
--exogenous holidays.csv \
--horizon 14 \
--freq D
Parameters:
--input: Historical time series CSV file--exogenous: Exogenous variables CSV file (optional)--horizon: Number of periods to forecast--freq: Time series frequency (D=daily, H=hourly, M=monthly, etc.)The script automatically:
Error: Exogenous data missing 'ds' column
Solution: Rename the date column in the exogenous data to 'ds'.
Error: Mismatch in date range between historical and exogenous data
Solution: Ensure the exogenous data covers the entire historical and forecast period.
Error: Exogenous variables have NaN values in the forecast horizon
Solution: Provide future values for exogenous variables for the entire forecast horizon.
Error: TimeGPT API rejected exogenous variables
Solution: Ensure exogenous variables are numeric and compatible with the TimeGPT API schema.
Error: NIXTLA_TIMEGPT_API_KEY environment variable not set
Solution: Set your TimeGPT API key as an environment variable before running the script.
Input (data.csv):
unique_id,ds,y
store_1,2024-01-01,100
store_1,2024-01-02,120
store_1,2024-01-03,115
Input (holidays.csv):
ds,holiday
2024-01-01,1
2024-01-02,0
2024-01-03,0
2024-01-04,0
Command:
python {baseDir}/scripts/integrate_exogenous.py \
--input data.csv \
--exogenous holidays.csv \
--horizon 7 \
--freq D
Output (forecast_exogenous.csv):
unique_id,ds,TimeGPT,TimeGPT-lo-90,TimeGPT-hi-90
store_1,2024-01-04,125,110,140
store_1,2024-01-05,128,113,143
Input (data.csv):
unique_id,ds,y
grid_1,2024-01-01 00:00,5000
grid_1,2024-01-01 01:00,5100
Input (weather.csv):
ds,temperature
2024-01-01 00:00,10
2024-01-01 01:00,8
2024-01-01 02:00,7
Command:
python {baseDir}/scripts/integrate_exogenous.py \
--input data.csv \
--exogenous weather.csv \
--horizon 24 \
--freq H
Output: Hourly forecast incorporating temperature trends.
{baseDir}/scripts/ directory contains all executable codetools
This skill assists with managing database sharding strategies. It is activated when the user needs to implement horizontal database sharding to scale beyond single-server limitations. The skill supports designing sharding strategies, distributing data across multiple database instances, and implementing consistent hashing, automatic rebalancing, and cross-shard query coordination. Use this skill when the user mentions "database sharding", "sharding implementation", "scale database", or "horizontal partitioning". The plugin helps design and implement sharding for high-scale applications.
tools
This skill enables Claude to perform comprehensive database security scans using the database-security-scanner plugin. It is triggered when the user requests a security assessment of a database, including identifying vulnerabilities like weak passwords, SQL injection risks, and insecure configurations. The skill leverages OWASP guidelines to ensure thorough coverage and provides remediation suggestions. Use this skill when the user asks to "scan database security", "check database for vulnerabilities", "perform OWASP compliance check on database", or "assess database security posture". The plugin supports PostgreSQL and MySQL.
testing
This skill enables Claude to design and visualize database schemas. It leverages normalization guidance (1NF through BCNF), relationship mapping, and ERD generation to create efficient and well-structured databases. Use this skill when the user requests to "design a database schema", "create a database model", "generate an ERD", "normalize a database", or needs help with "database design best practices". The skill is triggered by terms like "database schema", "ERD diagram", "database normalization", and "relational database design".
tools
This skill enables Claude to manage database replication, failover, and high availability configurations using the database-replication-manager plugin. It is designed to assist with tasks such as setting up master-slave replication, configuring automatic failover, monitoring replication lag, and implementing read scaling. Use this skill when the user requests help with "database replication", "failover configuration", "high availability", "replication lag", or "read scaling" for databases like PostgreSQL or MySQL. The plugin facilitates both physical and logical replication strategies.