# Pattern Interrupt — effect skill for cuts & pacing

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page.

Every few seconds of a short, break the visual pattern: angle, zoom, graphic, sound hit, so attention resets.

- **Type:** [Effect](https://varg.ai/how-to/effects.md) · [Cuts & pacing](https://varg.ai/how-to/browse/skills/cuts.md)
- **Slug:** `pattern-interrupt`
- **Status:** live
- **Publisher:** HeyGen (community)
- **License:** Apache-2.0
- **Source:** https://github.com/heygen-com/hyperframes/tree/main/registry/components/beat-accent
- **Works in:** Claude Code, Claude.ai, Codex, Cursor, OpenClaw, Gemini CLI, Any MCP client, varg Studio
- **Requires:** ffmpeg, HyperFrames (npx hyperframes), Remotion, CapCut (by hand)
- **Cost:** Free — the take renders locally; generated footage, if any, bills by the model

## What it does

Built on [Beat Accent](https://github.com/heygen-com/hyperframes/tree/main/registry/components/beat-accent) by HeyGen (HyperFrames), Apache-2.0. The write-up and recipes below are varg's.

A sudden zoom, a cut to B-roll, an on-screen graphic, a flash or a sound effect at regular intervals.

**When:** Shorts, reels, TikToks and YouTube intros where viewers decide in seconds whether to stay.

**Watch out:** Interrupts that do not relate to the words feel random; tie each one to a beat of the script.

**Timing:** Every 2–4 s; each interrupt 3–10 frames

**Also called:** visual reset, retention cut, scroll stopper, hook reset

### In FFmpeg

Combine a punch-in segment, a 2-frame flash and a whoosh SFX at 3 s:
```bash
ffmpeg -i talk.mp4 -i whoosh.wav -filter_complex \
"[0:v]split[p][q];[p]trim=0:3,setpts=PTS-STARTPTS[w];\
 [q]trim=3,setpts=PTS-STARTPTS,crop=iw/1.2:ih/1.2,scale=1080:1920,setsar=1[t];\
 [w][t]concat=n=2:v=1:a=0,eq=brightness=0.6:enable='between(t,3,3.066)'[v];\
 [1:a]adelay=2950:all=1[s];[0:a][s]amix=inputs=2:normalize=0:duration=first[a]" \
  -map "[v]" -map "[a]" out.mp4
```

### In HyperFrames

`beat-accent` (impact flash + micro scale pulse), `editorial-flash-overlay`, a punch-in tween on `.inner`, plus an SFX `<audio>` clip.

### In Remotion

Schedule interrupts as an array of frames; render a `<Sequence>` per interrupt holding a scale change, a flash `<AbsoluteFill>` or an `<Audio>` SFX.

### In CapCut

Split every few seconds and alternate Scale, add a Flash/Shake effect or a sticker, and drop a whoosh from Audio → Sound effects.

### Ready-made components

- [Beat Accent](https://skills.varg.ai/component/hf.beat-accent/) (hyperframes): npx hyperframes add beat-accent
- [Editorial Flash Overlay](https://skills.varg.ai/component/hf.editorial-flash-overlay/) (hyperframes): npx hyperframes add editorial-flash-overlay
- [Impact Shake](https://skills.varg.ai/component/remocn.impact-shake/) (remocn): npx shadcn@latest add @remocn/impact-shake
- [Camera Shake](https://skills.varg.ai/component/hf.camera-shake/) (hyperframes): npx hyperframes add camera-shake

### Where this comes from

- [FFmpeg filters: crop](https://ffmpeg.org/ffmpeg-filters.html#crop)
- [FFmpeg filters: amix](https://ffmpeg.org/ffmpeg-filters.html#amix)
- [HyperFrames: HTML schema](https://hyperframes.heygen.com/reference/html-schema)

## Use when

- Shorts, reels, TikToks and YouTube intros where viewers decide in seconds whether to stay.

## Not for

- Interrupts that do not relate to the words feel random; tie each one to a beat of the script.

## Install

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg`
- Codex: `npx skills add vargHQ/skills --skill varg-video-edit-library -a codex -y`
- Cursor: `npx skills add vargHQ/skills --skill varg-video-edit-library -a cursor -y`

## Example output

https://s3.varg.ai/how-to/previews/1abd07c1d4ef/take-pattern-interrupt.mp4 — zoom-in between two shots, with the timeline strip of the edit. Footage: Tears of Steel (2012), (CC) Blender Foundation | mango.blender.org, CC BY 3.0; WING IT! (2023), Blender Studio | studio.blender.org, CC BY 4.0. (credit: Rendered by varg · Tears of Steel (2012) + WING IT! (2023))

## More cuts & pacing skills

- [SmartCut (capcut-ai-editor)](https://varg.ai/how-to/skills/capcut-smartcut-mcp.md): MCP that reads CapCut auto-captions to cut silences and duplicate takes right inside your CapCut project.
- [Auto-Editor](https://varg.ai/how-to/skills/auto-editor.md): CLI that cuts dead space by loudness or motion and exports MP4 or editor timelines; now also an agent skill.
- [AutoCut](https://varg.ai/how-to/skills/autocut.md): Edit video in a text editor: Whisper transcribes, you delete lines in Markdown, AutoCut cuts the video.
- [Cut Video](https://varg.ai/how-to/skills/cut-video.md): Claude Code skill that tightens long recordings with forced-aligned cuts, keeping laughs and comedic pauses.
- [Videogrep](https://varg.ai/how-to/skills/videogrep.md): Search spoken words across videos and auto-build supercuts of every match.
- [PySceneDetect](https://varg.ai/how-to/skills/pyscenedetect.md): Find cuts, fades and scene changes in a video, then split it or export scene lists for the edit.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt