Communitygithub.com

video-editing-skill — Hormozi Captions + Jump-Cut Ship

Natural-language video edit: trim, silence jump-cuts, Hormozi/standard/minimal Whisper caption burn-in, text overlays, speed — pure Bash+FFmpeg+Whisper. Zero Python runtime. Composable for OpenClaw/Claude/Codex launch deliverables.

What is video-editing-skill — Hormozi Captions + Jump-Cut Ship?

Launch Video Step 3 (captions/ship): 6missedcalls/video-editing-skill. Take the four-beat polished cut → silence jump-cuts + Hormozi word-punch captions so mute feeds convert. Pure Bash pipeline.

Works with~Claude Code✓Codex CLI~Cursor
npx skills add 6missedcalls/video-editing-skill

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Video Editing

Edit videos using natural language instructions. Supports trimming, jump cuts (silence removal), captions with multiple styles, text overlays, and speed changes — all powered by ffmpeg and Whisper.

Usage

Give a video file path and describe what you want done:

Edit my video at ~/video.mp4 — remove silence, add Hormozi-style captions, and speed it up 1.25x
Trim ~/interview.mp4 from 00:02:00 to 00:15:00 and add standard captions
Add a "Subscribe!" text overlay at the 1 minute mark in ~/video.mp4

Capabilities

Trimming

Cut video to specific start/end timestamps or duration.

scripts/trim.sh video.mp4 --start 00:01:30 --end 00:05:00

Jump Cuts (Silence Removal)

Auto-detect and remove silent/dead-air sections. Configurable threshold, minimum silence duration, and padding.

scripts/jumpcut.sh video.mp4 --threshold -30 --duration 0.5 --padding 0.1

Captions

Transcribe audio with Whisper, then burn subtitles into video. Three caption styles:

StyleDescription
hormoziBold, centered, large — Alex Hormozi word-by-word impact style
standardTraditional bottom subtitles with semi-transparent background
minimalSmall lower-third captions, clean and unobtrusive
scripts/transcribe.sh video.mp4 --model base --language en
scripts/caption.sh video.mp4 video.srt --style hormozi

Text Overlays

Add text at specific positions and timestamps. Supports 7 positions: center, top, bottom, top-left, top-right, bottom-left, bottom-right.

scripts/overlay-text.sh video.mp4 --text "Subscribe!" --start 00:01:00 --end 00:01:05 --position bottom-right

Speed Changes

Adjust playback speed (audio pitch-corrected via atempo).

# Via edit.sh orchestrator
scripts/edit.sh video.mp4 --speed 1.5

Full Pipeline (Orchestrator)

Chain multiple operations in a single command:

scripts/edit.sh video.mp4 \
  --trim-start 00:00:10 --trim-end 00:10:00 \
  --jumpcut \
  --caption --caption-style hormozi \
  --speed 1.25 \
  --overlay-text "Like & Subscribe" --overlay-start 00:01:00 \
  --output final.mp4

Pipeline order: trim → jump cut → speed → caption → overlay

Requirements

  • ffmpeg — video processing (must be installed)
  • whisper — audio transcription for captions (openai-whisper CLI)

Scripts Reference

ScriptPurpose
scripts/edit.shMain orchestrator — chains all operations
scripts/transcribe.shWhisper transcription → SRT file
scripts/caption.shBurn SRT captions into video with style
scripts/trim.shTrim by timestamps
scripts/jumpcut.shAuto-remove silence via silencedetect
scripts/overlay-text.shAdd positioned text overlays

Agent Instructions

When the user asks to edit a video:

  1. Parse the request — identify which operations are needed (trim, jumpcut, caption, overlay, speed)
  2. Use edit.sh for multi-operation edits — it chains operations in the correct order
  3. Use individual scripts for single operations — faster, simpler output
  4. For captions: if the user has an existing SRT, use --caption-srt; otherwise transcription runs automatically
  5. Default caption style: use "standard" unless the user specifies a style
  6. Default whisper model: use "base" for speed; suggest "medium" or "large" for accuracy on long/noisy videos
  7. Output: always tell the user the output file path and duration

Related Skills