haipipe-data-2-record

Process SourceSets into temporally-aligned RecordSets with configurable pipelines.

Updated Feb 16, 2026

Search Tags:#data processing #data structuring #record pipeline #temporal alignment #cgm data #machine learning data

Ready to run

npx skills add https://github.com/jluo41/research-skills --skill haipipe-data-2-record

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: haipipe-data-2-record
Source: https://github.com/jluo41/research-skills/tree/main/skills/haipipe-data-2-record
Command: npx skills add https://github.com/jluo41/research-skills --skill haipipe-data-2-record

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill transforms raw data into temporally-aligned, structured records, making it ready for further analysis and machine learning pipelines.

Core Features & Use Cases

Temporal Alignment: Organizes data into consistent time intervals (e.g., 5-minute grids for CGM data).
Data Structuring: Creates a RecordSet containing Human and Record objects for efficient access.
Use Case: Convert raw CGM sensor readings and patient event logs into a unified, time-series dataset suitable for diabetes research.

Quick Start

Run the Record_Pipeline using the provided YAML configuration file to process the SourceSet into a RecordSet.

Frequently Asked Questions about haipipe-data-2-record

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

FAQPage Schema

How do I process raw CGM data into temporally-aligned records for machine learning?▼

Data structuring for machine learning involves transforming raw sensor streams into standardized time intervals. This pipeline aligns readings into configurable grids like 5-minute buckets, creating structured RecordSets ready for downstream analysis.

What is the best way to align time-series data into a structured record format?▼

Aligning time-series data into a structured record format requires a configurable pipeline that maps raw SourceSets into temporal grids. The output is a structured RecordSet containing Human and Record objects for efficient access.

Can I configure the time intervals when structuring raw data into records?▼

Yes, you can configure time intervals when structuring raw data into records. The pipeline supports domain-specific alignment strategies, enabling you to apply specific temporal grids like 5-minute intervals for CGM data.

How do I inspect and design pipeline components for data structuring?▼

You can inspect and design pipeline components for data structuring using multiple built-in subcommands. These allow you to inspect SourceSets, run the pipeline, and design alignment components to generate structured RecordSets.

Do I need a YAML configuration file to process data into structured records?▼

Yes, you need a YAML configuration file to process data into structured records. You run the record pipeline using this provided YAML file to transform your SourceSet into a temporally-aligned RecordSet.