agentleFS
Sign inStart free
hamzafarooqhamzafarooq/claude-code-starter/.claude/skills/youtube-deepdive/SKILL.md

youtube-deepdive

Skill145 starsChanged 6 months agoMITView on GitHub

Takes one or more YouTube video URLs, visits each page using Brave MCP, extracts chapters/timestamps, key moments, and top comments, and produces a structured highlight report. Use when the user wants to find the best parts of a video without watching the whole thing.

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. Very specific:

    If the description is collapsed, look for an "expand" or "more" button ref and click it — mcp__brave-devtools__browser_click

    line 29
  2. Distinctive:

    Use plain English throughout — this is for PMs, not engineers

    line 67
  3. Distinctive:

    Do not fabricate timestamps or quote comments you didn't read from the page

    line 68
  4. Distinctive:

    If the video page is unavailable (private, deleted, region-blocked), say so and skip it

    line 69
  5. Distinctive:

    If no chapters exist, do your best to infer structure from the description text

    line 70
  6. Very specific:

    After the write-up, ask: "Want me to save this to docs/youtube-deepdive.md?"

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

What this skill does

Given one or more YouTube video URLs, this skill visits each video page and extracts:

  • Chapters and timestamps from the description
  • Key moments (if YouTube shows them)
  • The video description summary
  • Notable comments that highlight key takeaways

It then produces a structured "highlight reel" report so the user can jump straight to the best parts.

How to execute

For each video URL provided:

  1. Navigate to the video URL — mcp__brave-devtools__browser_navigate
  2. Take a snapshot — mcp__brave-devtools__browser_snapshot
  3. Look for:
    • Chapters/timestamps in the description (lines starting with 0:00, 1:23, etc.)
    • Key moments panel YouTube sometimes renders on the page
    • Description text — first 3-5 sentences summarizing the content
    • Top comments — scroll or look for comment section in snapshot; extract 2-3 that mention specific tips or moments
  4. If the description is collapsed, look for an "expand" or "more" button ref and click it — mcp__brave-devtools__browser_click
  5. Repeat for each video
  6. Close the browser when done — mcp__brave-devtools__browser_close

Output format

Produce this write-up directly — no preamble:

YouTube Deep Dive: [Video Title]

Channel: [channel name] | URL: [link] | Duration: [duration if visible]

What it's about

1-2 sentences from the description. Plain English.

Best parts to watch

TimestampWhat happensWhy it matters
0:00......
2:15......

(If no timestamps are available, note that and summarize the key sections based on the description.)

What viewers found valuable

2-3 highlights from top comments (quote briefly, note what they're reacting to).

Should you watch it?

One sentence verdict — who this is for and whether it's worth the full runtime.

(Repeat the above block for each video.)

Rules

  • Use plain English throughout — this is for PMs, not engineers
  • Do not fabricate timestamps or quote comments you didn't read from the page
  • If the video page is unavailable (private, deleted, region-blocked), say so and skip it
  • If no chapters exist, do your best to infer structure from the description text
  • After the write-up, ask: "Want me to save this to docs/youtube-deepdive.md?"

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.

Reviews can't be read right now.

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