data-research

Name: data-research
Availability: InStock
Author: starlink-awaken

Extract structured data from emails, web sources, and APIs into tracker pages.

Updated Jun 10, 2026

Search Tags:#automation #data extraction #research #pipeline #deduplication #tracking

Ready to run

npx skills add https://github.com/starlink-awaken/omostation-gbrain --skill data-research-starlink-awaken

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/starlink-awaken/omostation-gbrain/tree/main/skills/data-research
Command: npx skills add https://github.com/starlink-awaken/omostation-gbrain --skill data-research-starlink-awaken

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of manual data collection and tracking by automating the extraction of structured information from emails, web sources, and APIs into organized, canonical tracker pages.

Core Features & Use Cases

Parameterized Research Pipelines: Uses YAML-based recipes to define custom extraction schemas for diverse data types like investor updates, expenses, or company metrics.
Extraction Integrity: Implements a robust 7-phase pipeline that ensures data accuracy by saving raw sources before extraction and using deterministic regex with LLM fallbacks.
Use Case: Automatically monitor your inbox for incoming investor update emails, extract key financial metrics like MRR and burn rate, and append them to a centralized markdown tracker table with backlinks to the original source.

Quick Start

Use the data research skill to initialize a new tracker recipe for monitoring monthly company revenue updates.

Frequently Asked Questions about data-research

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

FAQPage Schema

How do I automate extracting structured data from emails and web sources?▼

You can automate data extraction by defining custom YAML research recipes that process heterogeneous sources like emails and APIs, extracting structured data into organized tracker pages.

How do I track financial metrics from incoming investor update emails?▼

Tracking financial metrics involves monitoring your inbox for specific emails, applying deterministic regex extraction for data like MRR, and appending the results to a centralized markdown table.

Does this data extraction pipeline preserve the original raw source for auditing?▼

Yes, the data extraction pipeline saves raw sources before extraction to ensure data integrity and auditability, providing backlinks to the original source within your tracker.

What is the best way to deduplicate extracted data in a research pipeline?▼

The best way to deduplicate extracted data is using an automated pipeline that implements built-in deduplication and archival phases alongside deterministic regex extraction.

Can I use custom YAML recipes to define extraction schemas for company metrics?▼

Yes, you can use parameterized YAML-based recipes to define custom extraction schemas for diverse data types, including company metrics, investor updates, and expenses.

What happens when deterministic regex fails to extract structured data?▼

When deterministic regex fails to extract structured data, the pipeline uses LLM fallbacks to ensure data accuracy while maintaining the integrity of the research pipeline.