000-docs/000a-planned-skills/core-forecasting/nixtla-timegpt2-migrator/SKILL.md
Assists users in migrating their codebase and data pipelines from TimeGPT-1 to TimeGPT-2. Use when upgrading to the latest version of TimeGPT, ensuring compatibility, and optimizing performance. Trigger with "migrate to TimeGPT-2", "upgrade TimeGPT", "TimeGPT compatibility".
npx skillsauth add intent-solutions-io/plugins-nixtla nixtla-timegpt2-migratorInstall 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.
Facilitates a smooth transition from TimeGPT-1 to TimeGPT-2.
Automates the migration process from TimeGPT-1 to TimeGPT-2, identifying compatibility issues and generating updated code.
Evaluates existing TimeGPT-1 workflows for compatibility with TimeGPT-2. Identifies potential breaking changes and suggests necessary code modifications. Employs API checks and data schema validation. Provides updated code snippets and configuration examples for TimeGPT-2. Generates a migration report summarizing the changes required.
Tools: Read, Write, Edit, Glob, Grep
Environment: NIXTLA_TIMEGPT_API_KEY
Packages:
pip install nixtla pandas matplotlib statsforecast pyyaml
Scan the codebase for TimeGPT-1 API usage patterns using the analysis script.
Script: {baseDir}/scripts/analyze_codebase.py
Usage:
python {baseDir}/scripts/analyze_codebase.py /path/to/your/codebase
The script searches for:
timegpt.forecast() callstimegpt.create_model() callstimegpt.load_data() callstimegpt.train() callsOutput: analysis_report.txt listing all TimeGPT-1 usage instances.
Execute the compatibility checker to validate data schema and identify unsupported features.
Script: {baseDir}/scripts/compatibility_check.py
Usage:
python {baseDir}/scripts/compatibility_check.py --data sample_data.csv
The script validates:
Output: migration_report.txt with compatibility assessment.
Use the migration script to update your codebase with TimeGPT-2 compatible code.
Script: {baseDir}/scripts/apply_migration.py
Usage:
python {baseDir}/scripts/apply_migration.py main.py
The script performs automatic replacements:
timegpt.forecast() → client.forecast()from timegpt import TimeGPT → from nixtla import NixtlaClienttimegpt = TimeGPT() → client = NixtlaClient(api_key=...)timegpt.create_model() callsImportant: Review all changes before committing to version control.
Create a TimeGPT-2 configuration file with recommended settings.
Script: {baseDir}/scripts/generate_config.py
Usage:
python {baseDir}/scripts/generate_config.py
Output: timegpt2_config.yaml with configuration parameters.
Error: TimeGPT-1 API endpoint not found
Solution: Ensure TimeGPT-1 API is accessible or skip API validation step.
Error: Incompatible data schema
Solution: Update data input format to match TimeGPT-2 requirements (unique_id, ds, y columns).
Error: Missing API Key
Solution: Set the NIXTLA_TIMEGPT_API_KEY environment variable.
Error: Unsupported TimeGPT-1 feature
Solution: Refactor code to use equivalent TimeGPT-2 functionality or alternative approaches.
Error: File not found during migration
Solution: Verify the file path and ensure the file exists before running the migration script.
Before (TimeGPT-1):
from timegpt import TimeGPT
timegpt = TimeGPT()
forecast = timegpt.forecast(data, h=24)
After (TimeGPT-2):
from nixtla import NixtlaClient
import os
client = NixtlaClient(api_key=os.getenv('NIXTLA_TIMEGPT_API_KEY'))
forecast = client.forecast(df=data, h=24, freq='H')
Before (config.json):
{
"model": "timegpt-1",
"horizon": 24
}
After (timegpt2_config.yaml):
api_key: YOUR_API_KEY_HERE
model_name: TimeGPT-2
frequency: H
forecast_horizon: 24
data_format: Nixtla
# Step 1: Analyze codebase
python {baseDir}/scripts/analyze_codebase.py ./my_project
# Step 2: Check compatibility
python {baseDir}/scripts/compatibility_check.py --data ./data/sample.csv
# Step 3: Apply migration (review migration_report.txt first)
python {baseDir}/scripts/apply_migration.py ./my_project/main.py
# Step 4: Generate config
python {baseDir}/scripts/generate_config.py
{baseDir}/scripts/ directory contains all migration toolstesting
This skill enables Claude to manage isolated test environments using Docker Compose, Testcontainers, and environment variables. It is used to create consistent, reproducible testing environments for software projects. Claude should use this skill when the user needs to set up a test environment with specific configurations, manage Docker Compose files for test infrastructure, set up programmatic container management with Testcontainers, manage environment variables for tests, or ensure cleanup after tests. Trigger terms include "test environment", "docker compose", "testcontainers", "environment variables", "isolated environment", "env-setup", and "test setup".
tools
This skill uses the test-doubles-generator plugin to automatically create mocks, stubs, spies, and fakes for unit testing. It analyzes dependencies in the code and generates appropriate test doubles based on the chosen testing framework, such as Jest, Sinon, or others. Use this skill when you need to generate test doubles, mocks, stubs, spies, or fakes to isolate units of code during testing. Trigger this skill by requesting test double generation or using the `/gen-doubles` or `/gd` command.
tools
This skill enables Claude to generate realistic test data for software development. It uses the test-data-generator plugin to create users, products, orders, and custom schemas for comprehensive testing. Use this skill when you need to populate databases, simulate user behavior, or create fixtures for automated tests. Trigger phrases include "generate test data", "create fake users", "populate database", "generate product data", "create test orders", or "generate data based on schema". This skill is especially useful for populating testing environments or creating sample data for demonstrations.
development
This skill analyzes code coverage metrics to identify untested code and generate comprehensive coverage reports. It is triggered when the user requests analysis of code coverage, identification of coverage gaps, or generation of coverage reports. The skill is best used to improve code quality by ensuring adequate test coverage and identifying areas for improvement. Use trigger terms like "analyze coverage", "code coverage report", "untested code", or the shortcut "cov".