ingest

Route and parse content inputs into a structured knowledge graph.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of fragmented information by automatically routing, parsing, and linking incoming data into a structured, searchable knowledge graph.

Core Features & Use Cases

  • Automated Entity Detection: Automatically identifies people, companies, and concepts in every message to build a persistent knowledge graph.
  • Multi-Format Ingestion: Handles meetings, articles, media, and documents with specialized workflows for each, ensuring provenance via source citations.
  • Iron Law Back-linking: Enforces strict cross-referencing between entities, ensuring that every mention is connected to its source and context.

Quick Start

Use the ingest skill to process the meeting transcript provided in the latest email and update the relevant entity pages.

Frequently Asked Questions about ingest

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

FAQPage Schema
How do I build a knowledge graph from meeting transcripts and web articles?

To build a knowledge graph from meeting transcripts and web articles, you need automated entity extraction to identify people and concepts, then enforce back-linking to maintain source provenance across all synchronized ingested pages.

What is the best way to track source provenance during content ingestion?

Tracking source provenance during content ingestion requires applying strict cross-referencing between extracted entities and their original inputs, ensuring every mention connects directly to its source context via synchronized back-links.

Can I use automated entity detection to organize messy media files and documents?

Yes, automated entity detection organizes messy media files and documents by parsing diverse inputs, extracting people and concepts, and routing them into a structured, searchable knowledge graph with consistent state management.

How does multi-format ingestion work for fragmented information?

Multi-format ingestion for fragmented information works by routing and parsing diverse content inputs through specialized workflows, extracting entities and events to link everything into a single structured knowledge graph.

Does this knowledge management approach maintain consistent state across all ingested pages?

Yes, this knowledge management approach maintains consistent state across all ingested pages by applying automated entity detection and strict back-linking rules to synchronize every extracted mention with its source context.

When do I need a self-wiring knowledge graph for personal data?

You need a self-wiring knowledge graph for personal data when fragmented information from meetings, articles, and media requires automated entity routing and strict back-linking to become a structured, searchable database.