brain-add-video
Skill1 starsChanged 5 months agoMITView on GitHub
Process a YouTube or video URL into the second brain. Extracts transcript, metadata, and key points. Creates a structured video note with wiki-links.
- Installs packages
In this repository14 other files it gives its agents.
- brain-addSkill
- brain-checkSkill
- brain-digestSkill
- brain-processSkill
- brain-saveSkill
- brain-searchSkill
- client-onboardSkill
- consulting-deckSkill
- good-morningSkill
- harvestSkill
- logSkill
- taskSkill
- weekly-reviewSkill
- wrap-sessionSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 12 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 43
Remove duplicate consecutive lines (VTT often repeats lines across cue boundaries)
- Distinctive: line 45
If transcript is very long (>5000 words), work with the full text but focus the summary
- Very specific: line 52
Create 3-8 inline [[wiki-links]] for key concepts
- Distinctive: line 55
Use WebFetch on the URL to get the page metadata and video description
- Distinctive: line 56
Create a lighter note from title + description + any available info
- Distinctive: line 65
Use the actual content to decide, not assumptions.
- Very specific: line 94
If strong matches found, add to related: frontmatter (bidirectionally)
- Very specific: line 100
Add new entry in the appropriate category section: - [[note-name]](category/subcategory/note-name.md) — One-line summary.
- Distinctive: line 101
Update the note count in the header and the section header count
- Distinctive: line 102
Update "Last updated: YYYY-MM-DD"
- Distinctive: line 105
Use Bash to append directly without reading:
- Very specific: line 128
If yt-dlp is not installed, tell the user to run brew install yt-dlp and stop.
- Very specific: line 129
If yt-dlp fails entirely (network error, video unavailable), try WebFetch as fallback.
- Distinctive: line 130
If the video is very long (>1 hour), still process it but note the duration and focus the summary on the most substantive sections.
- Distinctive: line 131
If category is ambiguous, ask the user rather than guessing.
- Distinctive: line 135
Always read brain-config.md first.
- Distinctive: line 136
Do not create duplicate notes — search by source URL first.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/brain-add-video <YouTube URL>
Process a video URL into a structured brain note. Extracts transcript via yt-dlp, summarizes content, and files the note in the appropriate category.
Video URL Patterns
Recognized as video URLs:
youtube.com/watch?v=youtu.be/youtube.com/shorts/youtube.com/live/vimeo.com/
Steps
- Read
brain-config.md(taxonomy, tags, filing signals) andbrain-config-rules.md(processing rules, video pipeline, MOC rules). - Validate input — confirm the argument is a video URL (matches one of the patterns above). If not a video URL, suggest using
/brain-addinstead and stop. - Extract metadata via yt-dlp:
This returns 4 lines: title, channel, duration (e.g. "12:34"), upload date (YYYYMMDD).yt-dlp --skip-download --print title --print channel --print duration_string --print upload_date "<URL>" - Extract transcript via yt-dlp:
Then read the resultingyt-dlp --write-auto-sub --sub-lang "en.*" --sub-format vtt --skip-download --no-warnings -o "/tmp/brain-video-transcript" "<URL>".vttfile from/tmp/. - Clean the transcript:
- Strip VTT headers and timestamp lines (lines matching
XX:XX:XX.XXX --> XX:XX:XX.XXXorWEBVTTorKind:or position/align metadata) - Remove duplicate consecutive lines (VTT often repeats lines across cue boundaries)
- Join into readable paragraphs
- If transcript is very long (>5000 words), work with the full text but focus the summary
- Strip VTT headers and timestamp lines (lines matching
- If transcript is available:
- Summarize the video in 2-3 sentences
- Extract 5-10 key points as bullets
- Pull out notable quotes (verbatim from transcript)
- Identify actionable takeaways
- Create 3-8 inline
[[wiki-links]]for key concepts
- If transcript is NOT available (yt-dlp finds no subtitles):
- Use WebFetch on the URL to get the page metadata and video description
- Create a lighter note from title + description + any available info
- Set
status: seedand add a note: "No transcript available — revisit to enrich manually"
Determine category by matching content against filing signals in brain-config.md. Most video content will likely land in:
professional/ai-marketing— marketing, content strategy, LinkedInprofessional/tools-tech— software tutorials, AI toolspersonal/learning— educational content, coursespersonal/philosophy— mindset, leadership, values
Use the actual content to decide, not assumptions.
- Check for duplicates — search brain for existing notes with the same source URL or very similar title. If found, suggest updating instead of creating.
- Create the note file:
- Path:
brain/{category}/{subcategory}/{kebab-case-title}.md - Full YAML frontmatter:
--- title: "Video Title" type: video tags: [video, tag2, tag3] source: "https://youtube.com/watch?v=..." channel: "Channel Name" duration: "12:34" published: "2026-01-15" created: YYYY-MM-DD updated: YYYY-MM-DD status: seed category: professional related: [] summary: "One-line summary" --- - Body structured per video template (Summary, Key Points, Notable Quotes, Takeaways, Action Items)
- 3-8 inline
[[wiki-links]]in the body text
- Path:
- Check for connections:
- Grep across brain/ for notes sharing tags or referencing the same [[topics]]
- If strong matches found, add to
related:frontmatter (bidirectionally)
- Clean up — remove temporary transcript files from
/tmp/brain-video-transcript* - Update index.md:
- Read
brain/index.md - Add new entry in the appropriate category section:
- [[note-name]](category/subcategory/note-name.md) — One-line summary. Tags: tag1, tag2 - Update the note count in the header and the section header count
- Update "Last updated: YYYY-MM-DD"
- Read
- Append to log.md (do NOT read the file — append only):
- Use Bash to append directly without reading:
echo '## [YYYY-MM-DD] ingest | {note-title} Filed to: {category}/{subcategory}. Source: video ({channel}, {duration}). {X} wiki-links created. ' >> brain/meta/log.md
- Use Bash to append directly without reading:
- Update hot cache:
- Rewrite
brain/meta/hot.mdwith updated recent activity, brain shape, and current themes - Keep under ~500 words
- Rewrite
- Confirm with:
🎬 Added to brain/{category}/{subcategory}/{filename}.md Video: {title} by {channel} ({duration}) Tags: #tag1 #tag2 #tag3 Links: [[topic1]], [[topic2]] Connected to: {count} existing notes Transcript: {yes/no}
Error Handling
- If
yt-dlpis not installed, tell the user to runbrew install yt-dlpand stop. - If
yt-dlpfails entirely (network error, video unavailable), try WebFetch as fallback. If that also fails, create a minimal seed note with just the URL. - If the video is very long (>1 hour), still process it but note the duration and focus the summary on the most substantive sections.
- If category is ambiguous, ask the user rather than guessing.
Important
- Always read brain-config.md first.
- Do not create duplicate notes — search by source URL first.
- The
videotag should always be included, plus 2-4 content-specific tags. - Format the
published:date as YYYY-MM-DD (convert from yt-dlp's YYYYMMDD format). - Clean up /tmp/ transcript files after processing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

