media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo sources into a brain.

174|144|Updated Jun 10, 2026
One-click install
npx skills add https://github.com/inbrainfun/inbrain --skill media-ingest-inbrainfun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media-ingest
Source: https://github.com/inbrainfun/inbrain/tree/main/skills/media-ingest
Command: npx skills add https://github.com/inbrainfun/inbrain --skill media-ingest-inbrainfun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingesting diverse media into a unified brain context is challenging; this skill provides a structured workflow to capture, summarize, and link media across formats.

Core Features & Use Cases

  • Cross-format ingestion of video, audio, PDF, book, screenshot, and GitHub repo content with provenance.
  • Entity extraction and back-link propagation to create interconnected brain pages for people and companies.
  • Phase-driven processing: save raw sources, create brain pages by subject, and keep the index synchronized.

Quick Start

Use media-ingest to ingest a media item by providing its URL or file path and target brain context.

Frequently Asked Questions about media-ingest

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

FAQPage Schema
How do I ingest video and PDF content into a unified knowledge base with provenance?

Cross-format media ingestion handles video, audio, PDF, book, screenshot, and GitHub repo sources by saving raw files, creating subject-based brain pages, and synchronizing the index with extracted entities and provenance backlinks.

Can I extract people and company entities from screenshots and audio files?

Yes, entity extraction processes screenshots and audio files to identify people and companies, automatically creating interconnected brain pages and propagating backlinks to maintain provenance across all ingested media formats.

What is the best way to index GitHub repositories into a brain context with backlinks?

Phase-driven processing ingests GitHub repositories by saving raw source files, extracting entities, and propagating backlinks to synchronize the index across concepts, people, companies, and sources automatically.

Does media ingestion support indexing raw source files across multiple formats?

Media ingestion supports indexing raw source files across video, audio, PDF, book, screenshot, and GitHub repo formats by utilizing raw source storage uploads and synchronizing indexes for concepts, people, companies, and sources.

How does backlink propagation work when ingesting diverse media formats?

Backlink propagation works during media ingestion by extracting people and company entities from cross-format sources and automatically linking them to interconnected brain pages, ensuring synchronized indexing and verifiable provenance.