skills.rest
Sigmacodeat
SigmacodeatCOMMUNITY
Explore all skills by this author →
GitHub

media-ingest

Convert media content into structured knowledge pages with entities and relationships.

Updated Jun 20, 2026
Search Tags:#knowledge graph#github analysis#entity extraction#pdf processing#video transcription#media ingestion
One-click install
npx skills add https://github.com/Sigmacodeat/subsumio-web --skill media-ingest-sigmacodeat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: media-ingest
Source: https://github.com/Sigmacodeat/subsumio-web/tree/main/server/skills/media-ingest
Command: npx skills add https://github.com/Sigmacodeat/subsumio-web --skill media-ingest-sigmacodeat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the challenge of turning scattered media sources like videos, PDFs, books, screenshots, and repositories into organized, searchable knowledge with useful analysis instead of raw content dumps.

Core Features & Use Cases

  • Multi-format ingestion: Processes video, audio, PDF, book, screenshot, and GitHub repository content with extraction and analysis workflows.
  • Knowledge graph enrichment: Extracts people, companies, and concepts while creating backlinks and timeline connections across brain pages.
  • Provenance-aware storage: Preserves raw source files and creates structured summaries with highlights, citations, and entity relationships.

Quick Start

Use the media-ingest skill to process this YouTube video and add its key insights and mentioned entities to my brain.

Frequently Asked Questions about media-ingest

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

FAQPage Schema
How do I turn a YouTube video into a structured knowledge graph with extracted entities?▼

To turn a video into a knowledge graph, video transcription is processed to extract entities, people, and concepts, which are then stored as structured knowledge pages with summaries and linked relationships.

What is the best way to extract entities and relationships from a PDF or book for research?▼

The best way to extract entities from a PDF or book is through media ingestion, which converts raw content into structured knowledge pages with summaries, highlights, citations, and entity relationships.

Can I ingest a GitHub repository and map its components into a knowledge graph?▼

Yes, you can ingest a GitHub repository to map its components into a knowledge graph. This process applies entity extraction and analysis workflows to transform repository content into connected, searchable knowledge pages.

Does media ingestion preserve the original source files when generating summaries?▼

Yes, media ingestion preserves original source files through provenance-aware storage. It maintains the raw source while generating structured summaries with highlights, citations, and entity relationships.

How do I create backlinks and timeline connections across different media formats?▼

To create backlinks and timeline connections across different media formats, the system extracts people, companies, and concepts during ingestion, propagating these relationships across linked brain pages within the knowledge graph.

What formats work with media ingestion for extracting people and concepts?▼

Supported formats for extracting people and concepts include video, audio, PDF, book, screenshot, and GitHub repository content. Each format undergoes extraction and analysis workflows to build structured knowledge pages.

Related Skills

Explore More Education & Research 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
mitchuskimitchuski

agentprivacy-knowledgegraph

Map entities and relationships across the 0xagentprivacy ecosystem.

Community
Advanced
PostergullyPostergully

signal-detector

Capture ideas and entity mentions from inbound messages into cross-linked brain pages.

Community
Advanced
NinatuziNinatuzi

media-ingest

Ingest videos, audio, PDFs, and GitHub repositories into a structured knowledge graph.

Community
Advanced