fabricate-trading-day

Name: fabricate-trading-day
Availability: InStock
Author: tankygranny05

Generate balanced pickle files of synthetic player transactions from CSV whale data.

2|Updated Jan 30, 2026

Search Tags:#data pipeline #financial data #synthetic data #trading data #pickle generation #data fabrication

Ready to run

npx skills add https://github.com/tankygranny05/agent-box --skill fabricate-trading-day

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: fabricate-trading-day
Source: https://github.com/tankygranny05/agent-box/tree/main/agent-box/seed/codex-skills/fabricate-trading-day
Command: npx skills add https://github.com/tankygranny05/agent-box --skill fabricate-trading-day

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the creation of realistic, yet synthetic, trading data for incomplete trading days, ensuring data pipelines can run even when real-time data is scarce.

Core Features & Use Cases

Synthetic Data Generation: Creates complete pickle files from partial CSV whale data.
Data Balancing: Adds fake players and PT transactions to ensure data integrity and balance.
Use Case: When you have only a few whale transactions for a trading day and need a full dataset for testing or analysis, this skill generates a 30-40K row pickle file.

Quick Start

Use the fabricate-trading-day skill to generate a pickle file for the trading day 2026_01_06 using the whale data located at /path/to/whale_data.csv.

Frequently Asked Questions about fabricate-trading-day

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

FAQPage Schema

How do I generate synthetic trading data for incomplete trading days?▼

To generate synthetic trading data for incomplete trading days, this Skill takes partial CSV whale data and balances it by adding fake players and PT transactions. It outputs a complete pickle file with 30-40K rows for testing.

How do I balance dataset row counts and financial equilibrium for trading data pipelines?▼

Balancing dataset row counts and financial equilibrium is achieved by injecting synthetic player transactions into the existing dataset. The Skill validates data integrity and types to ensure the final pickle file meets all row count and balance requirements.

What is the best way to create fake player transactions from partial CSV whale data?▼

The best way to create fake player transactions from partial CSV whale data is using a data fabrication Skill that automatically generates matching synthetic trades. It validates data types and row counts before outputting a ready-to-use pickle file.

Can I use this synthetic data generation approach for testing data pipelines with scarce real-time data?▼

Yes, you can use this synthetic data generation approach for testing data pipelines when real-time data is scarce. It fabricates realistic trading transactions to ensure pipelines can run continuously without waiting for complete daily datasets.

Does the generated pickle file go through data integrity validation before output?▼

Yes, the generated pickle file goes through strict data integrity validation before output. The Skill checks data types, validates row counts, and ensures financial equilibrium is met so the final synthetic dataset is ready for immediate use.

When should I not use synthetic trading data fabrication for my datasets?▼

You should not use synthetic trading data fabrication when your analysis requires exclusively real market transactions or actual whale behavior. Because it generates fake players to balance incomplete datasets, the output is suited for testing rather than factual financial analysis.