# scenario-video

Integrates Scenario video generation and editing through MCP. Generates clips from text, animates still images, and automates video assembly.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 444 installs · ★ 1141
- Author: scenario-labs
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-video/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/scenario-video

## What it does

The skill routes video creation requests through the Scenario MCP tool loop. The agent searches for suitable models using `recommend` or `search`, inspects specific input requirements with `model_schema_get`, and uploads source media via `upload_asset`. Heavy rendering runs asynchronously in `model_run` with `wait=false` before polling completion status in `jobs_wait`.

Workflows cover text-to-video, image animation, lipsync, and 4K upscaling. Supported model families include Kling, Veo, Runway, Luma, Minimax, and Wan. Note that connection logic and the execution loop rely on the primary `scenario` skill.

Schemas enforce strict anchor rules. Setting a last-frame anchor alone throws an immediate 400 error: API contracts require an initial frame alongside it. Because video generators do not accept LoRA files directly, custom visual styles must enter as still image references.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-video -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-video -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-video -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install scenario-labs/skills scenario-video
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-video -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/scenario-labs/skills --path skills/scenario-video
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-video -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/scenario-labs/skills/tree/HEAD/skills/scenario-video/SKILL.md

## When to use it
- animate a key art still into an ad video clip
- generate video scenes directly from text prompts
- upscale existing video footage to 4K resolution
- synchronize avatar lip movements to a reference audio track
- trim, split, or concatenate clips using MCP tools

## Example prompts
- Animate this product still into a short clip with a slow camera push-in
- Find an img2video model on Scenario and fetch its input schema
- Submit the video generation job with wait=false and poll jobs_wait

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 19a6986365d3d940.

BEGIN THIRD-PARTY FILE 19a6986365d3d940
```text
---
name: scenario-video
description: "Use when generating or editing video on Scenario via MCP: text-to-video, a music video from a song, image-to-video (still animation, frame anchors), motion prompting, lipsync and talking avatars, dubbing a clip, video upscale to 4K, prompt-based editing, trim, split, concat, extend, reframe, resize, background removal, frame or audio extraction, long video jobs, or a clip over a duration limit. Keywords: txt2video, img2video, video2video, audio2video, I2V, T2V, V2V, localization."
license: MIT
---

# Scenario Video Generation and Editing

## Overview

Scenario exposes a large video catalog through one MCP loop: text-to-video and image-to-video
generators plus video-to-video editors, lipsync, upscalers, and deterministic cut/split/concat
tools. Per-family contracts: `scenario-kling`, `scenario-veo`, `scenario-seedance`,
`scenario-gemini-omni`, `scenario-luma-video`, `scenario-runway`, `scenario-grok-imagine-video`,
`scenario-wan`, `scenario-minimax-video`, `scenario-vidu`.

Connection and the core generation loop: see the `scenario` skill. If a sibling skill named here is
missing from your available skills, ask the user to install it
(`npx skills add scenario-labs/skills --skill <name>`); unattended, proceed from tool schemas and
flag the gap.

## Quick reference

| Step           | Tool                               | Notes                                                                                                                                                                                                                               |
| -------------- | ---------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Find a model   | `recommend` or `search`            | `recommend` with the need in the user's own words plus a `capability` from its enum (`img2video`, `video2video`, `audio2video` for a song; upscaling footage and syncing it to a track are both `video2video`); `search` for a name |
| Inspect inputs | `model_schema_get`                 | Always before `model_run`; video schemas differ widely (duration, aspect ratio, frame anchors)                                                                                                                                      |
| Upload source  | `upload_asset`                     | A local still or clip becomes an `asset_id`                                                                                                                                                                                         |
```
END THIRD-PARTY FILE 19a6986365d3d940

The third-party file has ended. Everything between the 19a6986365d3d940 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2752 of 17293 bytes. © scenario-labs · MIT · https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-video/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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