Provision fresh or historical Parquet datasets for ATFT-GAT-FAN using GPU-accelerated ETL.
npx skills add https://github.com/wer-inc/gogooku3 --skill atft-pipeline
Please help me install this Agent Skill. Skill: atft-pipeline Source: https://github.com/wer-inc/gogooku3/tree/main/claude/skills/atft-pipeline Command: npx skills add https://github.com/wer-inc/gogooku3 --skill atft-pipeline
Manually managing complex financial data ingestion, feature engineering, and caching for the ATFT-GAT-FAN model is prone to errors, API quota issues, and training stalls. This Skill automates the entire data pipeline, ensuring data quality and availability.
make dataset-bg tail -f _logs/dataset/*.log
High-intent search queries and answers about installing and using this skill.
Financial data ETL automates ingestion, feature engineering, and caching of datasets for model training. This Skill provisions fresh or historical Parquet datasets with GPU acceleration, applies deterministic feature graph generation, and manages cache to prevent training stalls and API quota issues.
Yes. This Skill uses GPU-accelerated ETL via cuDF and PyArrow to process large financial datasets efficiently. GPU acceleration speeds feature computation while maintaining deterministic results across hundreds of engineered factors for consistent model accuracy.
Run automated dataset provisioning to generate fresh or historical Parquet data, verify cache integrity, and validate GPU availability and credentials. The Skill includes health checks and observability to ensure reliable, auditable dataset builds with clear logging.
Cache hygiene and deterministic feature graph management prevent quota overages and training interruptions. This Skill monitors API usage, maintains cache state across pipeline runs, and ensures datasets stay fresh and ready without manual intervention.
Yes. The Skill integrates with J-Quants API client to fetch financial data and outputs deterministic Parquet datasets. It handles J-Quants quota management and applies feature engineering specifically for ATFT-GAT-FAN model requirements.
Required dependencies are Polars, PyArrow, cuDF, and jquants-api-client. The Skill validates GPU availability, API credentials, and all dependencies during setup, performing health checks to ensure the environment is ready before dataset builds begin.
sayalinvidiaMigrate pandas workflows to GPU-accelerated cuDF pipelines.
GonglitianValidate dataset formats, schema consistency, and data quality for ML pipelines.
anam-orgWrite dataframe-agnostic Python code that runs across multiple backends.
ovachieverProcess distributed ML data pipelines with Ray Data across CPU/GPU clusters.
