data-research

Name: data-research
Availability: InStock
Author: Inbrain

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

174|144|Updated Jun 10, 2026

Search Tags:#automation #research #data #deduplication #extraction #sources #tracker

Ready to run

npx skills add https://github.com/inbrainfun/inbrain --skill data-research-inbrainfun

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured research pipelines turn scattered information into a canonical, organized data layer that powers trackers and reports.

Core Features & Use Cases

Define research recipes and pipelines to search sources, classify data, extract structured fields, and archive raw sources.
Deduplicate and backlink entities in a canonical tracker, enabling reproducible investor updates, company metrics, and donation tracking.
Use built-in recipes (investor-updates, expense-tracker, company-updates) to scaffold common workflows and extend with custom queries and schemas.

Quick Start

Run the research workflow to define a recipe, then run the 7-phase workflow to collect, extract, archive, deduplicate, and publish tracker entries.

Frequently Asked Questions about data-research

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

FAQPage Schema

How do I automate data extraction from email and web sources into a structured tracker?▼

Data deduplication resolves duplicate records by comparing extracted entities and applying backlink enrichment to maintain a single, canonical entry within your tracker dataset during the update workflow.

Can I use built-in recipes for investor updates and expense tracking workflows?▼

Yes, built-in recipes for investor-updates, expense-tracker, and company-updates allow you to scaffold common workflows immediately, which you can then extend with custom queries and schemas.

What is a canonical tracker dataset and when do I need it for research pipelines?▼

A canonical tracker dataset is a deduplicated, organized data layer that powers reports. You need it when turning scattered information from email, web, or API sources into reproducible company metrics.

Does this data research workflow support API sources alongside email and web?▼

Yes, the data research workflow supports API sources alongside email and web, collecting scattered information to archive raw sources and automatically update your canonical tracker entries.