agentleFS
reescalderreescalder/claude-skills/tube-summary/SKILL.md

tube-summary

Skill0 starsChanged 4 months agoMITView on GitHub

Search YouTube for videos on any topic and get intelligent summaries from video subtitles. Use when you need to: (1) Find and preview YouTube videos on a subject, (2) Get a detailed description of what a video covers based on its actual content, (3) Quickly understand video topics without watching. Workflow: search YouTube → pick a video → extract and summarize subtitles.

  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search YouTube for videos on any topic, then extract and summarize their content using subtitles.

    line 8
  2. Distinctive:

    When asked about a topic, search YouTube and list the top 10 results:

    line 14
  3. Distinctive:

    Use the subtitle processor to analyze and summarize:

    line 38
  4. Distinctive:

    If YouTube search API is unavailable, the fallback uses web scraping via requests

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

tube-summary

Search YouTube for videos on any topic, then extract and summarize their content using subtitles.

Quick Start

Step 1: Search for Videos

When asked about a topic, search YouTube and list the top 10 results:

python3 scripts/youtube-search.py "your search query"

This returns a numbered list of videos with titles, channels, and view counts.

Step 2: User Picks a Video

The user selects one video by number (e.g., "3" for the third video).

Step 3: Download Subtitles

Extract English subtitles from the selected video using yt-dlp:

yt-dlp --write-subs --sub-langs en --skip-download "VIDEO_URL"

This creates a .en.vtt subtitle file without downloading the video.

Step 4: Process & Summarize

Use the subtitle processor to analyze and summarize:

python3 scripts/process-subtitles.py "path/to/subtitle-file.vtt"

This generates:

  • Key Topics: Main subjects covered in the video
  • Summary: Concise 2-3 paragraph description of content
  • Timestamps: Notable moments with context
  • Key Quotes: Important statements from speakers

Workflow

  1. Search → youtube-search.py "<topic>" → Display top 10 videos
  2. User selects → e.g., "Video 5"
  3. Extract URL → From the search results
  4. Download subs → yt-dlp --write-subs --sub-langs en --skip-download "URL"
  5. Process → process-subtitles.py "subtitle.vtt"
  6. Present → Formatted summary with key points

Prerequisites

  • yt-dlp (install: pip install yt-dlp)
  • requests (for YouTube search fallback)
  • Python 3.7+

Notes

  • If YouTube search API is unavailable, the fallback uses web scraping via requests
  • Subtitles may be auto-generated if not manually authored
  • Some videos may not have English subtitles available
  • The subtitle file is created in the same directory as yt-dlp is run

Example Usage

User: "Tell me about Rust programming language"

→ Search returns 10 videos about Rust

User: "Summarize video 3"

→ Downloads subtitles from video 3
→ Processes and returns detailed summary

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.