YouTube video summary

    1

    Extracts subtitles from video URLs to generate structured Markdown summaries and local transcript archives.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    YouTube video summary

    Example session with this skill installed

    Summarize this video: https://www.youtube.com/watch?v=dQw4w9WgXcQ. Focus on the production quality and save it to my summaries folder.

    • Read your context and instructions
    • Compiled the youtube video summary

    Rick Astley - Never Gonna Give You Up (Official Video) (4K Remaster)

    Topic and context
    Rick Astley's official music video for "Never Gonna Give You Up" (1987), remastered in 4K. It runs 3:33 and is performed by Rick Astley.

    Key ideas

    • A love song built on a promise of loyalty: never give you up, never let you down, never lie.
    • A classic 80s pop structure: two verses, a pre-chorus and chorus, a "(Ooh, give you up)" bridge, then the chorus three times to close.

    Production quality

    • This is based on the subtitles only. I didn't judge the picture, lighting, editing or mix.
    • The title says it's a 4K remaster, meaning the 1987 video was restored and upscaled.
    • The captions were made by hand and are clean, with music cues and backing vocals in brackets. That points to a polished official release.
    • The arrangement is built around the hook: the chorus plays five times, which is typical of producers Stock Aitken Waterman.

    Details and examples

    • The bridge uses call-and-response ("Never gonna give, never gonna give / (Give you up)"), layering the lead and backing vocals.
    • The lyrics barely change, and the second verse is repeated.

    Conclusion
    A carefully packaged official release of a classic hit, refreshed in 4K. To judge the visual production you'd need to watch the video.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    When you need the core value of a video without sitting through it, this skill extracts subtitles to generate structured summaries. It bypasses the need for video playback by processing transcript data directly, making it ideal for rapid research and documentation.

    What it does

    • Transcript extraction Fetches manual or auto-generated subtitles from YouTube and other yt-dlp supported platforms.
    • Smart chunking Handles long-form content by processing transcripts in 600-line segments to maintain context.
    • Multi-language support Summarizes content into your target language regardless of the original audio language.
    • Automated filing Saves summaries as formatted Markdown files in a dedicated directory if configured.

    How it works

    1. Fetch Use the internal script to retrieve the best available subtitle track and video metadata.
    2. Process Read the transcript file, using iterative chunking for videos exceeding the line limit.
    3. Summarize Draft a structured breakdown including context, key ideas, specific details, and conclusions.
    4. Archive Clean the filename and save the summary to the path specified in VIDEO_SUMMARY_DIR.

    Frameworks & tools

    Built with Python 3.8 and yt-dlp. It utilizes a custom transcript fetching script and optional browser cookie integration for restricted content.

    Why this beats prompting it yourself

    Standard prompts often fail on long videos due to context window limits or lack of direct subtitle access. This skill handles the technical fetch, manages large transcripts through chunked processing, and ensures output remains structured and localized.

    Use cases

    • Generate TL;DRs for long technical tutorials or webinars.
    • Extract key arguments from interviews or panel discussions.
    • Create a searchable library of video content in Markdown format.
    • Translate foreign language video content into readable reports.

    Known limitations

    Requires Python 3.8 and yt-dlp or uv. Cannot process videos that lack subtitle tracks or have restricted access without browser cookie intervention.

    Requires Python 3.8+ and yt-dlp. Cannot summarize videos without manual or auto-generated subtitles. May require browser cookies for age-restricted or members-only content.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    • Free with an Agensi account

    Requires

    Python
    yt-dlp
    uv (Python tool runner)
    uv (Python tool runner)

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    The skill uses yt-dlp to extract existing manual or auto-generated subtitle tracks directly from the URL, bypassing the need for audio-to-text processing and ensuring higher accuracy and speed.

    Yes, the skill utilizes a smart chunking system that processes long transcripts in 600-line segments, allowing it to summarize hours of footage without exceeding AI context window limits.

    You will receive the Python-based skill package, the custom transcript fetching scripts, and a configuration guide for setting up your local Markdown archive directory.

    The skill supports any platform compatible with yt-dlp (including YouTube and Vimeo); however, the video must have at least one available subtitle or closed-caption track to be processed.

    If you encounter age-restricted or private videos you have access to, you can configure the skill to use your browser's cookies to authenticate the fetch process.

    The output is fully customizable; the skill can translate and summarize the content into your preferred target language regardless of the video's original audio language.

    New in Workflow Automation