agentleFS
Sign inStart free
ilovefinikiilovefiniki/agent-skills/skills/youtube-summary-extractor/SKILL.md

youtube-summary-extractor

Skill0 starsChanged 48 days agoMITView on GitHub

Extract transcripts and generate structured summaries, executive takeaways, or actionable plans from YouTube videos directly without downloading video files. Use whenever the user shares a YouTube URL (video, short, podcast) and asks for a summary, key takeaways, transcript, or structured notes.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Run the extractor script with the video URL (or 11-char ID):

    line 26

≈ “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

YouTube Summary Extractor

Extracts complete transcripts and official chapters from YouTube videos in 1–2 seconds without downloading any video or audio files, and formats structured executive summaries tailored for technical, educational, and business content.

🛡️ Safety & Rate Limiting Guards

  • Zero Video Download: Pulls subtitles directly from YouTube's transcript API, saving bandwidth and disk space.
  • Rate Guard:
    • Maximum 20 requests per hour (rolling 60-minute window).
    • 5-second cooldown between successive requests.
    • State tracked in ~/.cache/youtube_rate_limit.json.
  • Zero Account Risk: Operates anonymously with no Google cookies or logins.

🚀 Execution Workflow

Step 1: Extract Transcript & Chapters

Run the extractor script with the video URL (or 11-char ID):

python3 scripts/extract_transcript.py "<YOUTUBE_URL>"

Returns JSON with:

  • title: Video title
  • channel: Creator / channel name
  • duration_formatted: e.g. 14:20
  • chapters: Official chapter marks (if provided)
  • chunks: Grouped transcript segments with timestamps
  • full_text: Complete transcript text

Step 2: Format Structured Summary

Format into a clean markdown document:

# 📺 [Video Title]
**Channel / Speaker:** {channel} | **Duration:** {duration_formatted} | [Watch on YouTube]({url})

---

### 📌 Core Takeaway (TL;DR / BLUF)
{2-3 concise sentences: core thesis, problem addressed, and final conclusion}

---

### 🧭 Timestamped Breakdown

#### ⏱️ 00:00 – {Chapter Title}
* {Key thesis}
* {Technical context / examples}

#### ⏱️ 04:30 – {Chapter Title}
* {Key thesis}
* {Actionable advice}

---

### 💡 Golden Nuggets & Key Quotes
* "{Direct quote or crucial insight}"

### 🛠️ Actionable Recommendations
- [ ] Task 1
- [ ] Task 2

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.

Check your setup, free