← ClaudeAtlas

video-ad-concept-editorlisted

Edit raw clips (AI-generated Veo/Gemini clips, phone/WhatsApp footage) into finished social ads with ffmpeg — clean the audio, cut dead air, remove AI watermarks, and re-cut one set of footage into MULTIPLE distinct concept versions by recombining voiceover and visuals independently. Trigger when the user wants to edit/cut/clean/arrange videos, make an ad from clips, produce 15s/30s shorts or multiple ad variants, remove noise or dead silence, remove a Gemini/Veo sparkle watermark, or add captions/text overlays — in any project under C:\Users\user\Desktop\video-ad.
abdul977/muahib-skills · ★ 0 · Code & Development · score 60
Install: claude install-skill abdul977/muahib-skills
# Video ad concept editor Turn a folder of raw clips into finished 9:16 social ads. The core idea that makes this skill different from naive cutting: > **Audio and video are not married.** Each clip is a voiceover block AND a > visual block, and they can be separated, re-ordered, and re-paired. A 44s set > of six clips is not "44s of material" — it is ~6 movable VO lines plus ~18 > distinct visual beats. That is what makes multiple genuinely different > concept versions possible from the same footage. ## Tools (all local, no network) | Tool | Path | |---|---| | ffmpeg | `C:\Users\user\Desktop\video-ad\tools\ffmpeg.exe` (no ffprobe — use `ffmpeg -i`) | | whisper.cpp | `...\tools\whisper\Release\whisper-cli.exe` | | whisper model | `...\tools\ggml-base.en.bin` | | fonts | `C:/Windows/Fonts/seguibl.ttf` (Segoe UI Black — best for punchy overlays) | Workspace layout: one folder per project; `assets/` raw in, `work/` intermediates, `output/` deliverables. ## The method ### 0. Lock the design system BEFORE you cut Do this first, every project. Without it you *will* drift: pick white-bordered text in one cut, invent a gold in the next, and ship a campaign with two visual languages. Decide once, write it to a file, reference it everywhere. **Derive the palette from the footage — never invent it.** Sample dominant and accent colours across every clip: ```python from PIL import Image; from collections import Counter im = Image.open(frame).convert("RGB") q = Counter(((r//32)*3