skills.rest
Postergully
PostergullyCOMMUNITY
Explore all skills by this author →
GitHub

media-ingest

Ingest video, audio, PDF, book, screenshot, and repository content into structured brain pages.

Updated May 4, 2026
Search Tags:#backlinks#media#provenance#transcripts#brain#ingest#entity-extraction
One-click install
npx skills add https://github.com/Postergully/11mirror-plugin --skill media-ingest-postergully
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: media-ingest
Source: https://github.com/Postergully/11mirror-plugin/tree/main/skills/media-ingest
Command: npx skills add https://github.com/Postergully/11mirror-plugin --skill media-ingest-postergully

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingesting diverse media into the brain requires consistent formatting, provenance, and backlinking to entities and pages. This skill automates ingestion of video, audio, PDF, book, screenshot, and GitHub repo content, generating structured brain pages and backlinks rather than raw dumps.

Core Features & Use Cases

  • Ingests multiple media formats (video, audio, PDF, book, screenshot, repo)
  • Creates a structured brain page with summary, entities, and backlinks
  • Preserves raw sources for provenance and allows subsequent entity propagation across pages
  • Supports back-linking for persons and companies mentioned

Quick Start

Provide a media URL or file and instruct the AI to ingest it using media-ingest.

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 transcripts and PDF documents into a structured knowledge base?▼

You can ingest video, audio, and PDF content into a structured knowledge base by providing a media URL or file. The system automatically extracts text, generates summaries, and creates cross-linked brain pages with entity extraction and provenance preservation.

Can I automatically extract entities and create backlinks from audio and video files?▼

Yes, automated entity extraction and backlinking from audio and video files creates structured brain pages. Persons and companies mentioned in the media are identified as entities and cross-linked across pages, preserving provenance and source data.

What is the best way to preserve provenance when ingesting media from a GitHub repository?▼

To preserve provenance when ingesting GitHub repository content, the system uploads raw sources via dedicated gbrain files before creating structured brain pages. This ensures original data integrity while generating summaries and propagating entity links.

Does media ingestion work with screenshots and book formats for entity extraction?▼

Media ingestion supports screenshots and book formats alongside video, audio, and PDF files. It handles text extraction from these formats, creates structured summaries, and propagates entity links with strict back-linking and error handling.

How to structure raw media dumps into searchable brain pages with cross-linking?▼

To structure raw media dumps into searchable brain pages, the ingestion process identifies the format, extracts text, preserves raw sources, and creates cross-linked pages. It propagates entity links and syncs indexes, transforming raw dumps into structured data.

What are the limitations when ingesting multiple media formats into the brain?▼

The ingestion process handles multiple media formats with strict error handling, but requires consistent formatting for successful brain page creation. Complex or corrupted media files may impact text extraction, entity propagation, and backlink generation quality.

Related Skills

Explore More Content & Communication Skills→
aresbitaresbit
46

summarize

Summarize URLs, local files, and video transcripts into concise summaries.

Community
Intermediate
edwifiguyedwifiguy
1

idea-ingest

Ingest and analyze shared links, articles, tweets, and ideas into the brain.

Community
Advanced
codysumpter-cloudcodysumpter-cloud
2

meeting-ingestion

Ingest meeting transcripts into brain pages with attendee details and entity links.

Community
Advanced
MantisWareMantisWare

reduce

Extract atomic claims with provenance from unstructured text sources.

Community
Intermediate