data-research

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

1|Updated Apr 11, 2026

Search Tags:#research #data #deduplication #extraction #web #emails #tracker

Ready to run

npx skills add https://github.com/edwifiguy/era-agents-ops --skill data-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/edwifiguy/era-agents-ops/tree/main/skills/era-agents-op/gbrain/skills/data-research
Command: npx skills add https://github.com/edwifiguy/era-agents-ops --skill data-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured data research from emails, web, and APIs into organized trackers, enabling repeatable data extraction and auditing.

Core Features & Use Cases

Built-in recipes for investor-updates, expense-tracker, and company-updates; custom recipes defined under ~/.gbrain/recipes/ to tailor sources, schemas, and tracker formats.
Seven-phase pipeline: define, search, classify, extract, archive, deduplicate, and update canonical tracker pages with backlinks.
Canonical trackers with backlink enrichment to support ongoing reporting and data governance.

Quick Start

Provide a research goal to initiate a recipe and start collecting, extracting, and tracking data using the gbrain workflow.

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 web pages to update a tracker?▼

To extract structured data from emails and web pages, this Skill uses a seven-phase pipeline to search, classify, and extract information, updating canonical tracker pages with backlinks for organized reporting.

What is the best way to deduplicate extracted data before feeding it into a canonical tracker?▼

The best way to deduplicate extracted data is using the pipeline's built-in deduplication phase, which processes extracted archives to ensure only unique structured records update your canonical tracker pages.

Do I need YAML recipes to extract investor updates and expense data?▼

Yes, you need YAML recipes to extract investor updates and expense data. The Skill includes built-in recipes for these use cases, but also supports custom YAML recipes stored locally under your recipes directory.

How does the data extraction pipeline classify and archive scattered research data?▼

The data extraction pipeline classifies and archives scattered research data by progressing through define, search, classify, and extract phases, scaffolding a local workspace to audit and structure the collected information.

Can I define custom extraction schemas and sources for specific company updates research?▼

Yes, you can define custom extraction schemas and sources for company updates research by creating custom YAML recipes, tailoring the seven-phase pipeline to fit your specific data governance and reporting needs.