skills.rest
weiping
weipingCOMMUNITY
Explore all skills by this author →
GitHub

media-ingest

Convert raw media sources into cross-linked brain pages with entity extraction.

1|Updated May 9, 2026
Search Tags:#knowledge graph#entity extraction#pdf ocr#youtube transcript#media ingest#backlink propagation#github repo summarization
One-click install
npx skills add https://github.com/weiping/gbrain-cn --skill media-ingest-weiping
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: media-ingest
Source: https://github.com/weiping/gbrain-cn/tree/main/skills/media-ingest
Command: npx skills add https://github.com/weiping/gbrain-cn --skill media-ingest-weiping

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the manual, error-prone process of converting scattered media sources (videos, audio, PDFs, books, screenshots, and GitHub repos) into usable, cross-linked knowledge inside your brain.

Core Features & Use Cases

  • Multi-format ingestion with analysis: Converts each media type into a proper brain page with a summary, highlights, and entity-aware structure instead of a transcript dump.
  • Entity extraction and back-link propagation: Detects every person and company mentioned, creates or enriches their pages, and adds back-links plus timeline entries.
  • Provenance-preserving raw uploads: Stores original source files for traceability using raw upload conventions.
  • Uses case examples: Ingest a podcast to produce a cited knowledge page, process a PDF of research to extract entities and chapters, or summarize a GitHub repo into an architecture-informed brain entry.

Quick Start

Ingest the provided YouTube link by running: ingest the YouTube/video into my brain and generate a cited media page with propagated person and company back-links.

Frequently Asked Questions about media-ingest

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

FAQPage Schema
How do I convert a YouTube transcript into a structured knowledge graph with entity extraction?▼

You can convert a YouTube transcript into a structured knowledge graph by ingesting the video link to generate a brain page with synthesis, entity extraction, and cross-linked back-links for all mentioned people and companies.

What is the best way to extract text from a PDF or book and build a cross-linked knowledge base?▼

The best way to extract text from a PDF or book for knowledge base enrichment is to ingest the file, which performs text and OCR extraction, summarizes content, and propagates timeline entries to detected entities.

Can I summarize a GitHub repo into an architecture-informed knowledge page?▼

Yes, you can summarize a GitHub repo into an architecture-informed brain entry by running the media ingest process, which converts repository data into a structured page with highlights and entity-aware cross-linking.

How does backlink propagation work when ingesting audio or video media?▼

Backlink propagation works by detecting every person and company mentioned during audio or video media ingestion, creating or enriching their specific pages, and automatically adding backlinks and timeline entries for provenance.

Does media ingestion preserve the original source files for traceability?▼

Yes, media ingestion preserves original source files for traceability by using provenance-preserving raw upload conventions, saving raw files by primary subject alongside the generated brain pages.

What formats and sources are supported for converting media into brain-ready knowledge?▼

Supported formats and sources for converting media into brain-ready knowledge include YouTube videos, audio transcription, PDF and book text or OCR extraction, screenshot OCR, and GitHub repository summarization.

Related Skills

Explore More Content & Communication Skills→
ltdrewltdrew
1

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into brain pages with entity extraction and backlink propagation.

Community
Advanced
Morris-UTRUSTMorris-UTRUST

gbrain-tcm-enrich

Enrich Chinese medicine entities from classical texts into a structured brain graph with citations and backlinks.

Community
Advanced
SigmacodeatSigmacodeat

ingest

Ingest unstructured content into a knowledge brain with citations and linked entities.

Community
Advanced
GYF0311GYF0311
5

media-ingest

Ingest videos, audio, PDFs, books, screenshots, and GitHub repos into structured brain pages.

Community
Advanced