Agent skill

Youtube Deepdive

by hamzafarooq in hamzafarooq/claude-code-starter

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.

MITAuto-check passed

Install Youtube Deepdive

skills CLI
$ npx skills add hamzafarooq/claude-code-starter --skill youtube-deepdive -a claude-code

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

GitHub CLI
$ gh skill install hamzafarooq/claude-code-starter youtube-deepdive --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/hamzafarooq/claude-code-starter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/youtube-deepdive .claude/skills/youtube-deepdive && 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-deepdive
GitHub stars
145
Token cost
~670 tokens
SKILL.md length
321 words
Files
1
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 6 steps: Navigate to the video URL —… → Take a snapshot —… → Look for → …
  • The user wants to find the best parts of a video without watching the whole thing
  • SKILL.md covers What this skill does, How to execute, Output format and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Youtube Deepdive is an agent skill from hamzafarooq/claude-code-starter. 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.

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with YouTube and Model Context Protocol. The licence is MIT.

When your agent uses it

  • The user wants to find the best parts of a video without watching the whole thing

Example prompts

  • “Use the youtube-deepdive skill to take one or more YouTube video URLs, visits each page using Brave MCP, extracts chapters/timestamps, key moments…”
  • “/youtube-deepdive”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Navigate to the video URL — mcpbrave-devtoolsbrowser_navigate
  2. Take a snapshot — mcpbrave-devtoolsbrowser_snapshot
  3. Look for
  4. If the description is collapsed, look for an "expand" or "more" button ref and click it — mcpbrave-devtoolsbrowser_click
  5. Repeat for each video
  6. Close the browser when done — mcpbrave-devtoolsbrowser_close

What it can do on your machine

Read from SKILL.md and the folder at commit 172c531. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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 Deepdive loads about 670 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~670

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 hamzafarooq/claude-code-starter at commit 172c531, republished under its MIT licence (© hamzafarooq). 321 words, ~670 tokens.

Download SKILL.mdSave it as .claude/skills/youtube-deepdive/SKILL.md (or your agent's skills folder).
name
youtube-deepdive
description
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.

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?"

© hamzafarooq, 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 .claude/skills/youtube-deepdive of hamzafarooq/claude-code-starter.

Open the folder on GitHubat commit 172c531

Compare with similar skills

Youtube Deepdive 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 Deepdive compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Youtube Deepdive this skillhamzafarooq/claude-code-starter145—~670Automated safety check: PassMIT
Multi-Source to NotebookLM Processorjoeseesun/qiaomu-anything-to-notebooklm6.2k—~3.6kAutomated safety check: PassMIT
SEO DataforseoAgriciDaniel/codex-seo7972 repos~4.6kAutomated safety check: PassMIT
Social PostHao0321/claude-skill-social-post729—~2.9kAutomated safety check: PassMIT
Video Perceptionjordanrendric/claude-video-vision1.4k—~1.4kAutomated safety check: PassMIT
Youtubeeat-pray-ai/yutu699—~1.1kAutomated safety check: PassMIT

Similar skills

  • 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 4 days ago
    Knowledge ManagementAuto-check passed
  • SEO Dataforseo

    AgriciDaniel/codex-seo

    Live SEO data via DataForSEO MCP server. An agent skill from AgriciDaniel/codex-seo.

    797 GitHub starsUsed in 2 repos~4.6k tokens
    Marketing & SEOAuto-check passed
  • Social Post

    Hao0321/claude-skill-social-post

    依使用者真實貼文與成效寫 Facebook/Instagram/YouTube/Threads/X 文案,包含 ChatGPT Chat 的「寫文」「Mode C」「用我的格式/口氣」「黑底白字」;本機工作台、規劃、確認後發布、留言回覆及成效學習。使用者說「發文」「文案」「Social Post 介面」「回覆留言」「查流量」「把數據訓練進去」「比較貼文」「優化 pattern」時使用。

    729 GitHub stars~2.9k tokensUpdated 6 days ago
    Writing & ContentAuto-check passed
  • Video Perception

    jordanrendric/claude-video-vision

    A skill your agent uses when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation

    1.4k GitHub stars~1.4k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Youtube

    eat-pray-ai/yutu

    A skill your agent uses whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation.

    699 GitHub stars~1.1k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed
  • Pullmd

    AeternaLabsHQ/pullmd

    Read any web page, document, or YouTube video as clean Markdown using PullMD.

    486 GitHub stars~2.6k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from hamzafarooq/claude-code-starter

All 29 skills in this repo
  • Beautiful HTML

    hamzafarooq/claude-code-starter

    Turn any document, proposal, report, or outline into a stunning single-file HTML presentation using 34 pre-built professional templates.

    145 GitHub stars~1.6k tokensUpdated 26 days ago
    Auto-check passed
  • Claude Code Deck

    hamzafarooq/claude-code-starter

    Generate a complete, ready-to-share HTML presentation explaining Claude Code, Skills, Sub Agents, Hooks, and Multi-Agent Systems — designed for product managers.

    145 GitHub stars~972 tokensUpdated 26 days ago
    Auto-check passed
  • Competitor Research

    hamzafarooq/claude-code-starter

    Research 3–5 competitors for any product or feature. An agent skill from hamzafarooq/claude-code-starter.

    145 GitHub stars~1.6k tokensUpdated 26 days ago
    Auto-check passed
  • Frontend Slides

    hamzafarooq/claude-code-starter

    Create stunning, animation-rich single-file HTML presentations from scratch or by converting a PowerPoint (.pptx) file.

    145 GitHub stars~1.4k tokensUpdated 26 days ago
    Auto-check passed
  • Md To PDF

    hamzafarooq/claude-code-starter

    Convert any markdown file to a clean PDF. An agent skill from hamzafarooq/claude-code-starter.

    145 GitHub stars~598 tokensUpdated 26 days ago
    Auto-check passed
  • User Story Writer

    hamzafarooq/claude-code-starter

    Converts feature ideas or rough bullets into user stories with acceptance criteria.

    145 GitHub stars~531 tokensUpdated 26 days ago
    Auto-check passed

Questions about Youtube Deepdive

What does Youtube Deepdive do?

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. Youtube Deepdive is an agent skill from hamzafarooq/claude-code-starter. 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.

When should I use Youtube Deepdive?

Youtube Deepdive fits situations like: the user wants to find the best parts of a video without watching the whole thing.

How do I install Youtube Deepdive in Claude Code?

Run `npx skills add hamzafarooq/claude-code-starter --skill youtube-deepdive -a claude-code`. Or copy the skill folder (.claude/skills/youtube-deepdive in hamzafarooq/claude-code-starter) into .claude/skills/youtube-deepdive in your project. Claude Code loads it when a task matches its description.

How do I install Youtube Deepdive in Codex?

Run `npx skills add hamzafarooq/claude-code-starter --skill youtube-deepdive -a codex`. Or copy the skill folder (.claude/skills/youtube-deepdive in hamzafarooq/claude-code-starter) into .agents/skills/youtube-deepdive in your project. Codex loads it when a task matches its description.

Can I use Youtube Deepdive 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 hamzafarooq/claude-code-starter --skill youtube-deepdive -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-deepdive, .gemini/skills/youtube-deepdive, .github/skills/youtube-deepdive and .opencode/skills/youtube-deepdive in your project.

What does Youtube Deepdive need to run?

SKILL.md names no scripts, command-line tools or credentials: Youtube Deepdive is instructions for the agent only.

Does Youtube Deepdive access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Youtube Deepdive 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 Deepdive use?

Youtube Deepdive 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 Deepdive use?

About 670 tokens (SKILL.md is roughly 2.7k 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 Deepdive?

Skills that share tags, products or a category with Youtube Deepdive: Multi-Source to NotebookLM Processor (joeseesun/qiaomu-anything-to-notebooklm, 6.2k stars), SEO Dataforseo (AgriciDaniel/codex-seo, 797 stars), Social Post (Hao0321/claude-skill-social-post, 729 stars) and Video Perception (jordanrendric/claude-video-vision, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Youtube Deepdive?

hamzafarooq (a GitHub user) maintains it in hamzafarooq/claude-code-starter, which has 145 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on September 13, 2026.

Source: hamzafarooq/claude-code-starter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.