skills.rest
starlink-awaken
starlink-awakenCOMMUNITY
Explore all skills by this author →
GitHub

data-research

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
One-click install
npx skills add https://github.com/starlink-awaken/omostation-gbrain --skill data-research-starlink-awaken
Or copy as Structured Prompt for Agent▼
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.

Related Skills

Explore More Data & Analytics Skills→
beyonaibeyonai
45

data-research

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

Community
Advanced
weipingweiping
1

data-research

Automates recurring web/data research workflows with configurable pipelines and tracked output.

Community
Advanced
ROLLED740ROLLED740
1

regex-vs-llm-structured-text

Parse structured text with regex extraction and conditional LLM validation.

Community
Advanced
pengfitpengfit

sichuan-price

Collect and synchronize Sichuan construction material prices to Elasticsearch.

Community
Advanced