# video-edit-assembly

video-edit-assembly turns a batch of video, audio and image files into one finished cut by picking the right clips, ordering them into a structure, and protecting full sentences of speech.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 297 repo stars
- Author: wwwzhouhui
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/wwwzhouhui/skills_collection/tree/HEAD/video-agent-kit/skills/video-edit-assembly/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/video-edit-assembly

## What it does

This skill takes over once `video-edit-agent` flags a job as multi-source assembly: combining several user-supplied clips into a montage, recap or social cut. It runs in phases — building a material inventory and parsing constraints like target duration, platform and tone, then probing each source with `inspect_media` and `transcribe`, then grouping clips into duplicates, off-topic shots and usable material. Keep-or-drop calls rely on contact sheets and transcripts rather than file names alone.

The skill is not built to use every clip supplied. Weak, repeated or off-topic footage gets dropped even when the cut falls short of the requested length. Where a source carries spoken dialogue, the skill either keeps a sentence whole or removes that spoken segment outright, so edits never land mid-thought. Output goes into `out/timeline.json` with tracks, assets and a stated editorial reason for each clip, while skipped material and assumptions are logged in `out/report.md`.

For vertical requests such as reels, shorts or TikTok cuts, the skill defaults to a 9:16 canvas unless that would hurt the footage; documentary or archival jobs keep the original landscape framing instead.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add wwwzhouhui/skills_collection --skill video-edit-assembly -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/video-edit-assembly/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/video-edit-assembly/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add wwwzhouhui/skills_collection --skill video-edit-assembly -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/video-edit-assembly/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add wwwzhouhui/skills_collection --skill video-edit-assembly -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/video-edit-assembly/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install wwwzhouhui/skills_collection video-agent-kit/skills/video-edit-assembly
```

2. **Manually: put the files in place**
- File: `.github/skills/video-edit-assembly/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add wwwzhouhui/skills_collection --skill video-edit-assembly -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/wwwzhouhui/skills_collection --path video-agent-kit/skills/video-edit-assembly
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/video-edit-assembly/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/wwwzhouhui/skills_collection/tree/HEAD/video-agent-kit/skills/video-edit-assembly/SKILL.md

## When to use it
- assemble one video from scattered clips, photos and audio
- cut duplicate or weak takes without manual sorting
- build a narrative arc: hook, development, climax, resolution
- keep spoken sentences intact instead of cutting mid-word
- prepare a timeline sized for vertical social formats

## Example prompts
- Assemble a reels recap from these clips without cutting any sentences mid-speech
- Build a montage from this folder of videos and photos in chronological order
- Pick the best takes and cut a 30-second TikTok edit

## Similar
- [scenario-video-assembly](https://affpapa.org/en/nevibecode/skills/scenario-video-assembly.md) — skill · 919 installs
- [fal-video-edit](https://affpapa.org/en/nevibecode/skills/fal-video-edit.md) — skill · 2900 installs
- [eachlabs-video-edit](https://affpapa.org/en/nevibecode/skills/eachlabs-video-edit.md) — skill · 353 installs
- [video-edit](https://affpapa.org/en/nevibecode/skills/0xsero-video-edit.md) — skill · ★ 92 repo stars
- [editing-montage](https://affpapa.org/en/nevibecode/skills/editing-montage.md) — skill · 408 installs
- [open-edit](https://affpapa.org/en/nevibecode/skills/open-edit.md) — skill · 1400 installs

From the same set: [wwwzhouhui/skills_collection](https://affpapa.org/en/nevibecode/by/wwwzhouhui/skills_collection.md) — 7 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
