media-ingest

Media Ingest Skill

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain.

Filing rule: Read skills/_brain-filing-rules.md (via get_skill _brain-filing-rules) before creating any new page.

Contract

This skill guarantees:

• Every ingested media item has a brain page with analysis (not just a transcript dump)
• Transcripts (video/audio) saved in raw and human-readable formats
• Entity extraction: every person and company mentioned gets back-linked
• Raw sources preserved via the put_raw_data tool
• Filing by primary subject, not by media format

Convention: See conventions/quality.md (via get_skill conventions/quality) for Iron Law back-linking.

Every mention of a person or company with a brain page MUST create a back-link.

Phases

Phase 1: Identify format and fetch

Format	Action
YouTube/video URL	Fetch transcript (Whisper, transcription service, or captions)
Audio file	Transcribe with available STT service
PDF	Extract text (OCR if needed)
Book PDF	Extract text, identify chapters/sections
Screenshot/image	OCR via vision model, extract text and entities
GitHub repo	Clone, read README + key files, summarize architecture (optionally memex index the checkout for code-graph queries)

Phase 2: Preserve raw source

Store the extracted text or transcript for provenance with put_raw_data, keyed to the page slug. Binaries themselves are not stored in the brain — record the original URL or file path on the page's **Source:** line.

Phase 3: Create brain page

File by primary subject (not format). Use this template:

# {Title}

**Source:** {URL or file path}
**Format:** {video/audio/PDF/book/screenshot/repo}
**Created:** {date}

## Summary
{Key points, not a transcript dump}

## Key Segments / Highlights
{For video/audio: timestamped highlights. For books: chapter summaries.}

## People Mentioned
{List with links to brain pages}

## Companies Mentioned
{List with links to brain pages}