data-research

Gather sources and extract fields into canonical tracker pages.

1|Updated May 12, 2026

Search Tags:#research #data #email #regex #structured-data #tracker

Ready to run

npx skills add https://github.com/ltdrew/Agent-brain-2 --skill data-research-ltdrew

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-research
Source: https://github.com/ltdrew/Agent-brain-2/tree/main/skills/data-research
Command: npx skills add https://github.com/ltdrew/Agent-brain-2 --skill data-research-ltdrew

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables end-to-end structured data research, from source gathering to canonical tracker updates, reducing manual effort and errors.

Core Features & Use Cases

Define recipes to specify sources, classification rules, and extraction schemas for consistent tracking.
Search and extract data from emails, web sources, and APIs, then archive raw inputs for auditability.
Update canonical trackers with deduplicated entries, backlinks, and running totals.

Quick Start

Create or customize a YAML recipe at ~/.gbrain/recipes/{name}.yaml and run the data-research pipeline to populate 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 into a tracker automatically?▼

To extract structured data from emails into a tracker, you define a YAML recipe specifying sources and extraction schemas. The pipeline searches emails, extracts fields deterministically, and updates a canonical tracker page with deduplicated entries.

What is a YAML recipe for structured data research?▼

A YAML recipe for structured data research is a configuration file stored at ~/.gbrain/recipes/. It specifies data sources, classification rules, and deterministic extraction schemas needed to consistently gather information and populate tracker pages.

Can I use regex to extract company metrics from web sources and APIs?▼

Yes, you can extract company metrics from web sources and APIs using deterministic extraction schemas. The pipeline applies your defined classification rules and regex patterns to gather data, archive raw inputs, and update running totals in trackers.

Does structured data research require manually formatting investor updates?▼

No, structured data research eliminates manual formatting of investor updates. By applying YAML recipes to emails, web sources, and APIs, the pipeline automatically extracts fields, deduplicates entries, and updates canonical tracker pages with backlinks.

What's the best way to build an expense tracker from multiple data sources?▼

The best way to build an expense tracker from multiple sources is using YAML recipes to define extraction schemas. The pipeline gathers data from emails, web, and APIs, archives raw inputs for auditability, and updates a standard tracker format.

Are there limitations when using deterministic extraction schemas for research?▼

Deterministic extraction schemas require predefined YAML recipes and consistent field structures. If source data from emails or APIs varies significantly from the regex classification rules, the canonical tracker updates may miss or incorrectly map the extracted fields.