data-research

Extract structured data from emails and web pages into canonical tracker pages.

Updated Jun 2, 2026
One-click install
npx skills add https://github.com/Ninatuzi/gbrain --skill data-research-ninatuzi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/Ninatuzi/gbrain/tree/main/skills/data-research
Command: npx skills add https://github.com/Ninatuzi/gbrain --skill data-research-ninatuzi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of fragmented, manual data collection by automating the extraction of structured information from emails, web sources, and APIs into a unified, searchable knowledge base.

Core Features & Use Cases

  • Structured Extraction Pipeline: Uses a 7-phase process to search, classify, extract, and archive data with built-in integrity checks.
  • Recipe-Based Automation: Supports custom YAML recipes for specific workflows like investor updates, expense tracking, or company metrics.
  • Use Case: Automatically monitor your inbox for investor update emails, extract key financial metrics like ARR and burn rate, and append them to a canonical tracker page 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 structured data extraction from unstructured sources like emails?

Create custom YAML recipes to define specific extraction workflows for automating investor updates, expense tracking, or company metrics. These parameterized recipes guide the pipeline to accurately parse unstructured sources and append structured metrics to your tracker pages.

How does deterministic extraction handle data deduplication and backlink consistency?

Deterministic extraction rules ensure data integrity by applying strict classification logic and deduplication checks during the 7-phase pipeline. This maintains backlink consistency by accurately mapping extracted structured data back to the original unstructured source.

Can I use this pipeline to monitor my inbox and extract financial metrics like ARR and burn rate?

Yes, you can monitor your inbox for investor update emails, extract key financial metrics like ARR and burn rate, and append them to a canonical tracker page. The pipeline automatically archives the data with backlinks to the original source email.

What is the best way to track company metrics from fragmented web sources and APIs?

The best way to track company metrics is deploying an automated extraction pipeline that pulls fragmented data from web sources and APIs into a searchable knowledge base. It uses built-in integrity checks to ensure clean, structured data archiving.

Do I need custom recipes to initialize a new tracker for monthly revenue updates?

Yes, you need custom YAML recipes to initialize a new tracker for monitoring monthly revenue updates. These recipes parameterize the extraction pipeline, allowing it to identify and parse the exact financial data points required from your unstructured sources.