Route inbound content into brain ingestion workflows with entity extraction and provenance citations.
npx skills add https://github.com/ngochuy13/intern-dev --skill ingest-ngochuy13
Please help me install this Agent Skill. Skill: ingest Source: https://github.com/ngochuy13/intern-dev/tree/main/skills/ingest Command: npx skills add https://github.com/ngochuy13/intern-dev --skill ingest-ngochuy13
It converts messy inbound content (meetings, articles, media, documents, and conversations) into structured, cross-referenced brain pages with provenance citations.
Use the ingest skill to ingest an item by saying: ingest this meeting/article/transcript, and route it into the brain with full provenance and entity cross-references.
High-intent search queries and answers about installing and using this skill.
To extract entities and events from meeting transcripts and documents, route the inbound content into an ingestion workflow that detects people, companies, concepts, and dates, then persists the updates into structured brain pages.
Organizing ingested articles and PDFs with timeline entries requires adding reverse-chronological timeline entries and maintaining Iron Law back-links between the extracted entity pages and the originally ingested content page.
Yes, you can ingest video and podcast transcripts. The ingestion process parses media transcripts with quotes and speaker attribution, while requiring transcript back-links and preserving the raw source via gbrain uploads.
Entity extraction works on PDFs and screenshots by extracting text from documents and images, including applying OCR when needed, to route the extracted content into specialized brain ingestion workflows.
To preserve raw source provenance when ingesting web pages and social posts, the ingestion process enforces mandatory provenance citations and preserves raw sources and transcripts for every ingested item via gbrain raw uploads.
A limitation of cross-referencing ingested content is that the workflow strictly enforces mandatory provenance citations and Iron Law back-links, meaning ingested items without raw source preservation via gbrain cannot be properly routed or persisted.
weipingRoute incoming content to ingestion workflows by detecting type and extracting entities.
Morris-UTRUSTIngests links, articles, tweets, and ideas into the brain with author pages and cross-links.
samuelmukotiExtract text from PDFs and documents using OCR and local parsers.
PostergullyParse inbound content and route it into brain pages with citations and back-links.
