agentleFS
carlosbuelvas1carlosbuelvas1/openclaw-skills/youtube-learn/SKILL.md

youtube-learn

Skill0 starsChanged 6 months agoMITView on GitHub

Use when Charlie sends a YouTube link and wants to learn from it, extract key ideas, find content angles, or build knowledge from the video.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill whenever Charlie drops a YouTube URL — no setup, no extra instructions needed.

    line 8
  2. Very specific:

    Call youtube_video_fetch with the URL to get title, channel, duration, description, and stats.

    line 17
  3. Very specific:

    Call youtube_transcript_fetch with the same URL.

    line 20
  4. Distinctive:

    If transcript fails, work from the title, description, and metadata only — do NOT mention the save path or any file operation in the output.

    line 21
  5. Distinctive:

    Create the directory if needed.

    line 66
  6. Distinctive:

    If the video is very long (1h+), focus key points on the densest 20% of the transcript.

    line 80

≈ “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 Learn

Use this skill whenever Charlie drops a YouTube URL — no setup, no extra instructions needed.

Trigger

Any message containing a YouTube URL (youtube.com, youtu.be, Shorts).

Workflow

Step 1 — Fetch video metadata

Call youtube_video_fetch with the URL to get title, channel, duration, description, and stats.

Step 2 — Fetch transcript

Call youtube_transcript_fetch with the same URL.

  • If transcript fails, work from the title, description, and metadata only — do NOT mention the save path or any file operation in the output.

Step 3 — Analyze and output

Produce the structured note below. Nothing else before it, nothing after it except the "WHAT WE CAN DO" section.


📺 [Title] — [Channel] ([Duration])

TL;DR 2 sentences. What this is actually about and why it matters.

KEY POINTS

  • [Real insight, not chapter heading]
  • [What was surprising or non-obvious]
  • [The thing most people miss]
  • [4th point if earned]
  • [5th point if earned]

BEST QUOTES

"[direct pull from transcript or description]" "[second pull]"

CONTENT ANGLES

  • [Specific article/post idea — not generic]
  • [Argument to make or counter]
  • [Hook, format, or frame worth stealing]

TAGS [tag1] [tag2] [tag3] [tag4]


🎯 WHAT WE CAN DO WITH THIS

Based on what was learned, give Charlie 2–3 concrete moves specific to his world:

  • Content he could create from this (specific angle, not "write about X")
  • A trading or business insight if one applies
  • A system, tool, or framework he could implement or test

These should feel like a smart operator speaking — not a list of suggestions. If something is obvious or generic, cut it.

Step 4 — Save silently

Save the full note as ~/.openclaw/workspace/knowledge/youtube/[YYYY-MM-DD]-[slug-from-title].md. Create the directory if needed. Do not mention the save in the output — just do it.

Voice

  • Be direct. Charlie reads fast.
  • Flag if something in the video is wrong, outdated, or oversimplified.
  • Content angles must be specific — not "write about mindset" but "write about why most people misread discipline as motivation."
  • The "WHAT WE CAN DO" section is the most valuable part. Make it earn its place.

Notes

  • Works on any YouTube video with captions/auto-captions.
  • Shorts work but transcripts are often unavailable — use metadata only.
  • Private videos will fail — tell Charlie immediately.
  • If the video is very long (1h+), focus key points on the densest 20% of the transcript.

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.