More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    YouTube Clipper: Turn Long Videos into Short Clips

    1

    Turn a long video into shareable clips — acquire the source, score every chapter for clip-worthiness, cut and reframe for vertical, burn in subtitles, and deliver a recap note.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    YouTube Clipper: Turn Long Videos into Short Clips

    YouTube Clipper: Turn Long Videos into Short Clips

    Example session with this skill installed

    Turn this 52-minute conference talk on community gardens into three vertical clips for Shorts, Reels, and TikTok, with burned-in subtitles.

    • Read your context and instructions
    • Compiled the youtube clipper

    Toolchain verified first: yt-dlp present, ffmpeg with subtitle rendering confirmed, and a subtitle parser ready — nothing discovered missing mid-run. Acquired the 52-minute talk at 1080p with uploaded English captions, and confirmed the title, duration, and file size with the user before cutting. Chapter mapping produced 14 fine-grain chapters, each scored on self-contained, hook, and right length. Three scored highest: the soil-mix demo at 08:12–09:04 (a vivid hands-on moment with a quotable line in the first 10 seconds), the watering-mistake story at 21:37–22:48 (a surprising claim that stands alone), and the harvest-numbers close at 47:05–48:11 (a concrete payoff for the whole talk). Each clip was cut with a few frames of handle on each side, reframed to 9:16 with the crop biased toward the speaker's hands and the demo table rather than the center, and given burned-in subtitles in bold white with a dark outline, two lines maximum, checked on three frames per clip — beginning, middle, end. The recap note lists the three clips with timestamps and one-line descriptions, a short paragraph on the talk's substance, and consistent file names, and the source files were kept until the user confirmed all three clips played clean.

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

    About this skill

    Long videos contain short videos trying to get out. This skill finds them: acquire the source, understand its structure, score every chapter for clip-worthiness, cut the moments the user picks, reframe them for vertical, burn in subtitles, and summarize what was made. It runs on yt-dlp and ffmpeg, needs no account and no credits, and ends with clips that are re-watched end to end before delivery plus a recap note that makes them findable in six months. Use it whenever a talk, lecture, or long video should become three tight clips instead of one link nobody watches to the end.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.

    It cuts the video you give it; it cannot fetch a video from a platform that blocks downloads.
    Auto-generated captions have timing quirks and misheard words — the skill notes which caption source was used and why it matters.
    Clips are excerpts for commentary, sharing, or personal use — check the licensing situation before publishing someone else's content as your own.

    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 buying a skill.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    Permissions

    No special permissions declared or detected

    Listed3 days ago

    What's inside

    Frequently Asked Questions

    No. The pipeline runs on yt-dlp and ffmpeg, both free, and the scoring and reframing are a written method you follow. No account, no credits.

    30–90 seconds for Shorts, Reels, and TikTok; up to 3 minutes for a highlight clip. The chapter score checks length before a segment is ever cut.

    Automated pipelines fail silently — frozen frames, audio drift, subtitle timing slip. Eyes catch what the log does not, so every clip is re-watched end to end, no exceptions.

    New in Image & Video