AIASys Notebook-first Workflow

What problem does it solve?

This Skill eliminates the risk of lost context, unreproducible results, and wasted effort caused by data analysts in AIASys using ad-hoc REPL workflows for analysis tasks, replacing them with a structured, persistent notebook-first approach.

Core Features & Use Cases

• Standardized Workflow Guidance: Defines a clear default process for listing existing notebooks, creating scratch notebooks for experiments, splitting analysis into logical cells, and executing code directly in notebooks.
• Explicit Editing Rules: Provides 12 targeted rules for notebook cell editing, execution, and management to prevent common errors like overwriting entire notebooks or mixing notebook and plain file editing semantics.
• Context Optimization: Includes concise data observation best practices to prevent large DataFrame outputs from consuming excessive context, ensuring fast and efficient analysis sessions.
• Use Case: Perfect for data analysts, researchers, and code experimenters working in AIASys who need to run reproducible data analysis, visualization, or modeling tasks that can be reviewed, continued, and shared with team members.

Quick Start

Load this skill before starting any data analysis, code experiment, or Python execution task in AIASys to follow the recommended notebook-first workflow.