skills.rest
Morris-UTRUST
Morris-UTRUSTCOMMUNITY
Explore all skills by this author →
GitHub

data-research

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

Updated May 16, 2026
Search Tags:#research#data#email#web#structured#deduplicate#tracker
One-click install
npx skills add https://github.com/Morris-UTRUST/GBrain-knowledge --skill data-research-morris-utrust
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/Morris-UTRUST/GBrain-knowledge/tree/main/skills/data-research
Command: npx skills add https://github.com/Morris-UTRUST/GBrain-knowledge --skill data-research-morris-utrust

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured research from email, web, and API sources; archive raw data, deduplicate, and update canonical trackers to keep datasets current and verifiable.

Core Features & Use Cases

  • A guided 7-phase pipeline that defines recipes, searches sources, classifies data, extracts structured fields, archives raw data, deduplicates entries, and updates canonical trackers with backlinks.
  • Built-in recipes (investor-updates, expense-tracker, company-updates) and a parameterized framework that adapts to recurring data collection tasks.
  • Backlink-enriched tracker pages that link entities to their canonical pages for audit and analysis.

Quick Start

Scaffold a new data-research recipe and run the investor-updates pipeline against your inbox and primary data sources to generate a tracker page.

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 and websites into a tracker?▼

To extract structured data from emails and websites, this Skill runs a 7-phase pipeline that searches sources, classifies data, extracts fields, and updates canonical trackers with backlinks. It archives raw data and deduplicates entries to keep datasets verifiable.

What is the best way to deduplicate recurring research entries from multiple sources?▼

The best way to deduplicate recurring research entries is using the built-in data-research pipeline, which archives raw sources, classifies extracted fields, and removes duplicate entries before updating canonical trackers to ensure dataset integrity.

Can I use a custom recipe for structured data extraction instead of the built-in templates?▼

Yes, you can use a custom recipe for structured data extraction. The Skill provides a parameterized framework alongside built-in recipes like investor-updates and expense-tracker, allowing you to adapt the pipeline to recurring data collection tasks.

Does the pipeline archive raw source data for audit purposes?▼

Yes, the pipeline archives raw source data for audit purposes. It logs raw sources during the extraction process and produces backlink-enriched tracker pages that link entities to their canonical pages for review and analysis.

How do I track investor updates and company news automatically?▼

To track investor updates and company news automatically, apply the built-in investor-updates or company-updates recipes. These recipes collect, classify, and extract data from your inbox and primary sources, then update a canonical tracker page for review.

What are the limitations of using a parameterized data-research pipeline for web scraping?▼

The parameterized data-research pipeline focuses on structured data extraction from emails, websites, and APIs using predefined recipes. It is designed for recurring data collection and archiving rather than broad, unstructured web scraping tasks without defined extraction fields.

Related Skills

Explore More Data & Analytics Skills→
zjykzkzjykzk

wiki-ingest

Ingest documents, text, and URLs into interconnected Obsidian wiki pages.

Community
Advanced
inbrainfuninbrainfun
174

data-research

Automate a 7-phase pipeline to extract, deduplicate, and update canonical tracker datasets.

Community
Advanced
yunusgungoryunusgungor

data-research

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

Community
Advanced
ngochuy13ngochuy13

data-research

Convert research inputs into structured, deduplicated tracker entries with raw-source archiving.

Community
Advanced