skills.rest
yunusgungor
yunusgungorCOMMUNITY
Explore all skills by this author →
Website𝕏@codevoygeeGitHub

data-research

Automate structured data collection from email, web, and APIs into canonical trackers.

Updated May 11, 2026
Search Tags:#research#data#email#deduplication#extraction#web#tracker
One-click install
npx skills add https://github.com/yunusgungor/gbrain --skill data-research-yunusgungor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/yunusgungor/gbrain/tree/main/skills/data-research
Command: npx skills add https://github.com/yunusgungor/gbrain --skill data-research-yunusgungor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the collection, extraction, and canonical tracking of structured data from emails, web sources, and APIs, turning unstructured sources into organized, deduplicated tracker pages.

Core Features & Use Cases

  • 7-phase pipeline for end-to-end data research: define recipes, search sources, classify, extract, archive, deduplicate, and backlink data.
  • Built-in recipes for investor updates, expenses, and company updates, with YAML recipes stored under ~/.gbrain/recipes.
  • Supports archiving raw sources and backlinking to entity pages, enabling reproducible data trails.

Quick Start

Configure a data-research recipe and run the pipeline to extract structured data from your sources.

Frequently Asked Questions about data-research

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

FAQPage Schema
How do I extract structured data from emails into a tracker?▼

You can extract structured data from emails by defining a recipe and running the 7-phase pipeline to search, classify, extract, deduplicate, and backlink data into a markdown tracker page with running totals.

What is the best way to automate research data collection from web sources and APIs?▼

Automating research data collection from web sources and APIs is done through customizable YAML recipes stored under ~/.gbrain/recipes, which drive the pipeline to archive raw sources and update canonical tracker pages.

Can I customize extraction recipes for investor updates and company updates?▼

Yes, you can customize extraction recipes for investor updates, expenses, and company updates by creating and modifying YAML files stored in the ~/.gbrain/recipes directory to fit your specific data collection needs.

How does deduplication work when collecting data from unstructured sources?▼

Deduplication works as a dedicated phase in the data research pipeline, ensuring that extracted data from unstructured emails, web sources, and APIs is organized into canonical trackers without redundant entries.

Does the data research pipeline support archiving raw sources for reproducibility?▼

Yes, the data research pipeline supports archiving raw sources and backlinking them to entity pages, which establishes reproducible data trails and maintains extraction integrity rules throughout the process.

Why do I need canonical trackers for unstructured data extraction?▼

Canonical trackers are needed for unstructured data extraction because they organize deduplicated information from emails and web sources into a structured markdown page with running totals, making the data actionable.

Related Skills

Explore More Data & Analytics Skills→
edwifiguyedwifiguy
1

data-research

Extract structured data from sources into canonical trackers using YAML recipes.

Community
Advanced
ltdrewltdrew
1

data-research

Gather sources and extract fields into canonical tracker pages.

Community
Advanced
PostergullyPostergully

data-research

Automate structured data research from emails, web sources, and APIs.

Community
Advanced
Morris-UTRUSTMorris-UTRUST

data-research

Extracts structured data from emails, websites, and APIs into canonical trackers via parameterized recipes.

Community
Advanced