Captures a YouTube video as a source note and a wiki page. An agent skill from superhero-tech/super-brain.

MITAuto-check passedKnowledge Management

Install Youtube

skills CLI
$ npx skills add superhero-tech/super-brain --skill youtube -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install superhero-tech/super-brain youtube --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/superhero-tech/super-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/7-Skills/youtube .claude/skills/youtube && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
youtube
GitHub stars
160
Token cost
~985 tokens
SKILL.md length
445 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Captures a YouTube video as a source note and a wiki page. An agent skill from superhero-tech/super-brain.

  • Works in 5 steps: Pull the metadata → Get the transcript → Classify the video → …
  • The human drops a video URL
  • SKILL.md covers When to use, Requirements, How to invoke and How it works, plus 2 more sections
  • Calls yt-dlp, brew and pip; reaches youtube.com

What it does

Youtube is an agent skill from superhero-tech/super-brain. Captures a YouTube video as a source note and a wiki page. Use when the human drops a video URL, wants a talk or tutorial turned into notes, or asks what a specific video said about a topic.

Its SKILL.md is about 990 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management. It works with YouTube. The repository describes itself as: Product Builder Second Brain - AI Product Heroes Edition 3. The licence is MIT.

When your agent uses it

  • The human drops a video URL
  • Tutorial turned into notes
  • Asks what a specific video said about a topic

Example prompts

  • “Use the youtube skill to capture a YouTube video as a source note and a wiki page. An agent skill from superhero-tech/super-brain”
  • “/youtube”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Pull the metadata
  2. Get the transcript
  3. Classify the video
  4. Generate the note
  5. Save the note and hand it to the ingest

What it can do on your machine

Read from SKILL.md and the folder at commit 0922a1a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • yt-dlp
    • brew
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • youtube.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Youtube loads about 985 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~985

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from superhero-tech/super-brain at commit 0922a1a, republished under its MIT licence (© superhero-tech). 445 words, ~985 tokens.

Download SKILL.mdSave it as .claude/skills/youtube/SKILL.md (or your agent's skills folder).
name
youtube
description
Captures a YouTube video as a source note and a wiki page. Use when the human drops a video URL, wants a talk or tutorial turned into notes, or asks what a specific video said about a topic.

YouTube Video Summary

Turns a YouTube video into a structured note, then compiles that note into a wiki page in Knowledge.

When to use

  • You want a video turned into a clean note with metadata and key ideas
  • For tutorials the output is a step-by-step guide, not a summary

Requirements

This skill pulls metadata and subtitles with yt-dlp. Install it once:

bash
brew install yt-dlp     # macOS
pip install yt-dlp      # everywhere else

Without yt-dlp the skill still works, just slower: take the video ID from the URL and search the web for the metadata, then ask the human to paste the transcript from YouTube's transcript panel. Say which route you are taking so they know why it takes longer.

How to invoke

  • /youtube https://youtube.com/watch?v=...
  • "Make a note from this video: [URL]"

How it works

1. Pull the metadata
bash
yt-dlp --skip-download --print "%(title)s|||%(channel)s|||%(upload_date)s|||%(description).500s" "$ARGUMENTS"

If yt-dlp fails: extract the video ID from the URL and use web search.

2. Get the transcript
bash
yt-dlp --skip-download --write-auto-subs --sub-langs "en" --sub-format "vtt" -o "/tmp/yt_transcript" "$ARGUMENTS"

Add more languages to --sub-langs when you need them. If it fails, ask the user to paste the transcript from YouTube.

3. Classify the video
  • Tutorial/Explainer: walkthrough, demo, how-to -> output a step-by-step guide
  • Idea/Opinion: thesis, interview, perspective -> output key ideas plus quotes
4. Generate the note

YAML frontmatter:

yaml
---
date: YYYY-MM-DD
title: "Video Title"
author: Channel Name
source: [YouTube URL]
topics:
  - topic-1
  - topic-2
source_type: video
---

This is the frontmatter of the source note that lands in 2-Inbox/ and later 5-Raw/. It is not wiki-page frontmatter - wiki pages use type: concept | entity. Do not copy this block onto the wiki page.

For tutorials:

markdown
# Title

## What this covers
[1-2 sentences]

## Step-by-Step
### Step 1: [Action]
[What to click, type, configure. Imperative.]

## Tips & Gotchas
- Practical notes and limitations

## Source
[URL]

For ideas/opinions:

markdown
# Title

## Key Ideas
- (5-10 key ideas - be specific)

## Summary
[3-5 paragraphs]

## Notable Quotes
> "Quote from the video"

## Source
[URL]

What to extract:

  • Concrete examples and anecdotes (do not abstract them away)
  • Numbers and metrics
  • "here is what we actually do" moments - where speakers reveal practice instead of theory
  • Contrarian claims
  • Tools and products by name
  • Metaphors and mental models
  • Q&A sections - the best nuggets hide there
Show full SKILL.md (166 more words)Show less
5. Save the note and hand it to the ingest

Save the note to 2-Inbox/, then run the ingest skill on it. That skill owns everything downstream: mapping the video against the wiki, writing the pages, linking them, updating the index and log, and archiving the note to 5-Raw/.

Tell the ingest one thing it cannot see on its own: talks are entity-heavy. The speaker, their company and every tool they name by name are entity candidates, and a good talk moves more pages than an article of the same length.

This skill's job ends at a note good enough to compile.

Self-check

  • Could someone hold a conversation about this topic reading only my note?
  • For tutorials: could someone RUN the workflow without watching the video?
  • Did I capture the concrete numbers and metrics?
  • Did I catch the Q&A section?
  • Did I avoid AI filler words (delve, tapestry, pivotal, foster)?
  • Is the note in 2-Inbox/ and handed to the ingest, rather than left sitting there?

Cleanup

bash
rm -f /tmp/yt_transcript*

© superhero-tech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in 7-Skills/youtube of superhero-tech/super-brain.

Open the folder on GitHubat commit 0922a1a

Compare with similar skills

Youtube next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Youtube compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Youtube this skillsuperhero-tech/super-brain160—~985Automated safety check: PassMIT
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k3 repos~3.2kAutomated safety check: PassNone
Multi-Source to NotebookLM Processorjoeseesun/qiaomu-anything-to-notebooklm6.2k—~3.6kAutomated safety check: PassMIT
Youtubeaxoviq-ai/synthadoc1.6k1 repos~634Automated safety check: PassAGPL-3.0-or-later
YouTube Transcript FetcherZeroPointRepo/youtube-skills1k1 repos~1.1kAutomated safety check: PassMIT
LLM Wikisdyckjq-lab/llm-wiki-skill2.5k1 repos~7kAutomated safety check: WarnMIT

Similar skills

  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 3 repos~3.2k tokens
    Knowledge ManagementAuto-check passed
  • Multi-Source to NotebookLM Processor

    joeseesun/qiaomu-anything-to-notebooklm

    Collects content from WeChat articles, web pages, YouTube, podcasts, documents and more, uploads it to NotebookLM and generates podcasts, slides or mind maps.

    6.2k GitHub stars~3.6k tokensUpdated 3 days ago
    Knowledge ManagementAuto-check passed
  • Youtube

    axoviq-ai/synthadoc

    Extract transcripts from YouTube videos via the YouTube caption system

    1.6k GitHub starsUsed in 1 repo~634 tokens
    Knowledge ManagementAuto-check passed
  • YouTube Transcript Fetcher

    ZeroPointRepo/youtube-skills

    Fetches the transcript of a YouTube video through TranscriptAPI.com so the agent can summarize, quote, translate or fact-check what was said.

    1k GitHub starsUsed in 1 repo~1.1k tokens
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    sdyckjq-lab/llm-wiki-skill

    个人知识库构建系统(基于 Karpathy llm-wiki 方法论)。让 AI 持续构建和维护你的知识库, 支持多种素材源(网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件), 自动整理为结构化的 wiki。

    2.5k GitHub starsUsed in 1 repo~7k tokens
    Knowledge ManagementAuto-check: warnings
  • LLM Wiki Upgrade

    sdyckjq-lab/llm-wiki-skill

    升级 llm-wiki 到最新版本。从 GitHub 拉取最新代码并通过官方 install.sh 升级核心主线. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub stars~735 tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check: notes

More from superhero-tech/super-brain

All 8 skills in this repo
  • Ingest

    superhero-tech/super-brain

    Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it.

    160 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Second Brain Setup

    superhero-tech/super-brain

    A skill your agent uses when creating or refreshing a product builder's personal profile in 8-System/about.md - supports both assessment-based (Gallup, DISC, MBTI) and interview-based onboarding

    160 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Feynman

    superhero-tech/super-brain

    Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin.

    160 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Lint

    superhero-tech/super-brain

    Health check over the compiled wiki in 4-Knowledge/, written up as a ranked report.

    160 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Query

    superhero-tech/super-brain

    Answers from the compiled wiki in 4-Knowledge/, with citations and a saved output file.

    160 GitHub stars~909 tokensUpdated 1 mo ago
    Auto-check passed
  • Project Start

    superhero-tech/super-brain

    Sets up a new project folder and runs the interview that fills its brief.

    160 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Youtube

What does Youtube do?

Captures a YouTube video as a source note and a wiki page. An agent skill from superhero-tech/super-brain. Youtube is an agent skill from superhero-tech/super-brain. Captures a YouTube video as a source note and a wiki page.

When should I use Youtube?

Youtube fits situations like: the human drops a video URL; tutorial turned into notes; asks what a specific video said about a topic.

How do I install Youtube in Claude Code?

Run `npx skills add superhero-tech/super-brain --skill youtube -a claude-code`. Or copy the skill folder (7-Skills/youtube in superhero-tech/super-brain) into .claude/skills/youtube in your project. Claude Code loads it when a task matches its description.

How do I install Youtube in Codex?

Run `npx skills add superhero-tech/super-brain --skill youtube -a codex`. Or copy the skill folder (7-Skills/youtube in superhero-tech/super-brain) into .agents/skills/youtube in your project. Codex loads it when a task matches its description.

Can I use Youtube in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add superhero-tech/super-brain --skill youtube -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/youtube, .gemini/skills/youtube, .github/skills/youtube and .opencode/skills/youtube in your project.

What does Youtube need to run?

Going by SKILL.md and its folder, Youtube needs the command-line tools its instructions call (yt-dlp, brew and pip). Our summary lists: Python 3.

Does Youtube access the network?

SKILL.md names 1 domain. In commands or code: youtube.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Youtube safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Youtube use?

Youtube is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Youtube use?

About 985 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Youtube?

Skills that share tags, products or a category with Youtube: Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars), Multi-Source to NotebookLM Processor (joeseesun/qiaomu-anything-to-notebooklm, 6.2k stars), Youtube (axoviq-ai/synthadoc, 1.6k stars) and YouTube Transcript Fetcher (ZeroPointRepo/youtube-skills, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Youtube?

superhero-tech (a GitHub organization) maintains it in superhero-tech/super-brain, which has 160 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 25, 2026.

Source: superhero-tech/super-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.