# universal-video-prompt-skill

universal-video-prompt-skill is a skill that separates a video brief from model-specific prompt formats and adapts it to an available generator. Use the same brief to compare models or reuse it.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 244 installs · ★ 46 repo stars
- Author: AtlasCloudAI
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AtlasCloudAI/atlas-cloud-skills/tree/HEAD/skills/universal-video-prompt-skill/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/universal-video-prompt-skill

## What it does

The skill guides the agent to split a video brief into whole-film rules, details that must stay fixed, and events over time. It favors outcomes that can be checked in the generated clip over vague directions. Skip sections that do not apply.

Next, the agent adapts the brief to a target model. The skill distinguishes portable wording from model-specific behavior, which should be tested with a small probe. If a capability is missing, it gives ways to simplify the plan and report the change. Without a model profile, the agent should test rather than assume what the generator supports.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add AtlasCloudAI/atlas-cloud-skills --skill universal-video-prompt-skill -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add AtlasCloudAI/atlas-cloud-skills --skill universal-video-prompt-skill -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add AtlasCloudAI/atlas-cloud-skills --skill universal-video-prompt-skill -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install AtlasCloudAI/atlas-cloud-skills skills/universal-video-prompt-skill
```

2. **Manually: put the files in place**
- File: `.github/skills/universal-video-prompt-skill/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add AtlasCloudAI/atlas-cloud-skills --skill universal-video-prompt-skill -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/AtlasCloudAI/atlas-cloud-skills --path skills/universal-video-prompt-skill
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add AtlasCloudAI/atlas-cloud-skills --skill universal-video-prompt-skill -a opencode
```

### 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/AtlasCloudAI/atlas-cloud-skills/tree/HEAD/skills/universal-video-prompt-skill/SKILL.md

## When to use it
- reuse one video brief across different models
- compare model outputs against a shared specification
- describe a clip through stages and visible end states
- adapt a brief when the intended model is unavailable

## Example prompts
- Write a video specification that I can adapt to different generators.
- Compare how the available video models handle this same brief.
- Check what needs to change if this model cannot follow the requested timing.

## Similar
- [video-prompting-guide](https://affpapa.org/en/nevibecode/skills/video-prompting-guide.md) — skill · 268 installs
- [ai-video](https://affpapa.org/en/nevibecode/skills/ai-video.md) — skill · 1200 installs
- [layer-video-direction](https://affpapa.org/en/nevibecode/skills/layer-video-direction.md) — skill · 1100 installs
- [ai-avatar-video](https://affpapa.org/en/nevibecode/skills/ai-avatar-video.md) — skill · 1000000 installs
- [video](https://affpapa.org/en/nevibecode/skills/video.md) — skill · 98700 installs
- [higgsfield-faceless-video](https://affpapa.org/en/nevibecode/skills/higgsfield-faceless-video.md) — skill · 36600 installs

From the same set: [atlascloudai/atlas-cloud-skills](https://affpapa.org/en/nevibecode/by/atlascloudai/atlas-cloud-skills.md) — 3 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
