- Home
- Skills
- Workflow Automation
- Gaming Clipper — Local VOD-to-Shorts
More screenshots
Works with the AI Agents you already use
Gaming Clipper — Local VOD-to-Shorts
Turn long YouTube VODs, Twitch/Kick streams, or local gameplay recordings into 1080x1920 Shorts, Reels, and TikToks locally — zero watermarks, zero monthly fees, using local hype detection and FFmpeg.
$10
Gaming Clipper — Local VOD-to-Shorts
Example session with this skill installed
Clip this 1-hour GTA stream into 3 viral vertical Shorts with hook titles, facecam split-screen, and word-synced captions: https://www.youtube.com/watch?v=MX8wnu3xXeM
- Read your context and instructions
- Compiled the gaming clipper
Summary
Downloaded MX8wnu3xXeM.mp4, analyzed audio energy peaks + word-level transcript locally with faster-whisper, and rendered 3 retention-structured 1080x1920 clips (-14 LUFS, 60fps, .metadata.txt included).
| Clip | Timeframe | Layout | Style | Hook Title |
|---|---|---|---|---|
kai_01_ending_c.mp4 | 3497.1s–3532.5s (35.4s) | gaming-split + facecam | classic | WAIT FOR WHAT THEY DO |
kai_02_checkers_fail.mp4 | 646.7s–669.0s (22.3s) | gaming-split + facecam | neon | BRO GOT DISTRACTED BY CHAT |
kai_03_gta_rank_clean.mp4 | 3721.4s–3765.0s (43.6s) | gaming-split (clean) | classic | SAN ANDREAS VS GTA 5 |
Commands executed
uv run python scripts/fetch_video.py --source "..." --max-height 720uv run python scripts/analyze_video.py --input workspace/source/MX8wnu3xXeM.mp4 --out workspace/analysis.jsonuv run python scripts/render_clip.py ... --out workspace/clips/kai_01_ending_c.mp4
Next steps
- Upload the rendered
.mp4files fromworkspace/clips/using the generated.metadata.txttitles and tags. - Run
uv run python scripts/cleanup.pywhen finished to free disk space.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop paying monthly fees for cloud clippers that slap watermarks on your videos. Gaming Clipper turns any AI coding agent into a 100% local, watermark-free VOD-to-Shorts studio.
What It Does
- 100% Local & Private: Uses
yt-dlp,faster-whisper, andFFmpegdirectly on your machine — zero API credits or subscriptions. - 2 Vertical Framing Modes:
gaming-split: Blurred 9:16 background + full 16:9 gameplay (keeps HUD visible) with optional corner facecam extraction (--cam-pos/--cam-box) stacked above gameplay.center-crop: Full-screen 9:16 crop for IRL, podcasts, and talking-head clips.
- 5 Caption Style Presets (
--style):classic(yellow),neon(cyan),emerald(green),fire(orange), andclean(white) — word-synced in the TikTok/Reels/Shorts safe zone. - Retention Polish: Auto-snaps clip starts to the first spoken word, burns 3–5 word hook titles, normalizes audio to
-14 LUFS, and exports.metadata.txtfor every clip. - GPU + CPU Support: Uses NVIDIA
h264_nvencwhen available and falls back to CPU (libx264+int8) automatically.
Local Machine Requirements
uv(Python 3.10+) andFFmpegonPATHyt-dlp,faster-whisper, andnumpy(installed locally viauv sync)
Open-source MIT core by Hammad Naveed: https://github.com/HmdNvd/Gaming-Clipper
Requires local FFmpeg and uv installation. Transcription speed and render times depend on user hardware (CPU/GPU).
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago
Requires
Permissions
File Scopes