ingest

Parse unstructured content into knowledge base pages with citations.

5|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/GYF0311/lorekit --skill ingest-gyf0311
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ingest
Source: https://github.com/GYF0311/lorekit/tree/main/brain/skills/ingest
Command: npx skills add https://github.com/GYF0311/lorekit --skill ingest-gyf0311

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns messy inputs like meetings, articles, media, and messages into structured, cross-linked brain pages with provenance citations so your knowledge base can compound over time.

Core Features & Use Cases

  • Smart ingestion router: Detects input type and delegates the work to the right ingestion workflows.
  • Entity-first brain filing: Creates or updates pages for people, companies, concepts, meetings, and sources following the filing rules.
  • Iron Law back-linking: Guarantees every entity mention produces a back-link from the entity page to the page that mentions it.
  • Timeline + event propagation: Writes timeline entries and propagates the same event across all relevant entity pages.
  • Mandatory provenance citations: Ensures every stored fact includes an inline [Source: ...] with date and origin.
  • Raw source preservation: Uploads and retains raw transcripts/files for verifiability, especially for media.

Quick Start

Tell your AI: ingest this meeting transcript and file it into brain pages with sources and back-links.

Frequently Asked Questions about ingest

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

FAQPage Schema
How do I ingest unstructured meeting transcripts into a structured knowledge base?

To ingest unstructured meeting transcripts into a knowledge base, the Skill parses entities, creates brain pages, and records events with mandatory provenance citations. It automatically routes inputs to specialized workflows while preserving raw source files for verifiability.

What is the best way to build a knowledge graph with entity extraction and back-linking?

Building a knowledge graph with entity extraction involves detecting entities in your content and applying Iron Law back-linking. This ensures every entity mention produces a back-link from the entity page to the mentioning page, creating a connected brain wiki.

Can I use this for ingesting articles and media into a wiki with provenance tracking?

Yes, you can use this for ingesting articles and media into a wiki with provenance tracking. It applies source parsing and strict citation rules to ensure every stored fact includes an inline source with date and origin, while uploading and retaining raw transcripts.

How does timeline propagation work across entity pages in a brain wiki?

Timeline propagation writes timeline entries and propagates the same event across all relevant entity pages. When ingesting unstructured content, the Skill detects entities, creates or rewrites their brain pages, and maintains synchronized event timelines throughout the knowledge base.

Does wiki compilation support automatic routing for different content types like meetings and documents?

Wiki compilation supports automatic routing for different content types through a smart ingestion router. It detects the input type, such as meetings, articles, or documents, and delegates the parsing and entity detection work to the appropriate specialized ingestion workflow.