Skip to main content
skill CX Codex

scenario-veo — Claude Code skill for video: features and install

scenario-veo is a Claude Code skill that generates and extends video with Google Veo through Scenario MCP. It handles text prompts, image references, and existing clips.

MIT 853 installs ★ 3,964 updated 2026-11-01

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add scenario-labs/skills --skill scenario-veo -a claude-code
Open on GitHub

What scenario-veo does

scenario-veo helps select a Veo model and prepare a video generation request for Scenario. It covers text-to-video, animation from an opening image, transitions between two stills, reference images for subject or style consistency, and clip extension. Model inputs and controls vary.

Requests can include dialogue, sound effects, and ambience. Every model requires the generateAudio parameter. The skill needs Scenario MCP and Veo models available in Scenario. Reference mode accepts only 8-second clips; extension works with 16:9 sources whose short side is 720p or 1080p.

What it helps with

  • generate a video from a text prompt
  • animate an image as the opening frame
  • create a transition between two still images
  • keep a subject or visual style consistent with references
  • extend a 16:9 clip

Example prompts for the agent

  • Make a video from this description and include spoken dialogue.
  • Animate this image as the opening frame, using the reference for visual style.
  • Extend this clip while keeping its 16:9 format.

How to install scenario-veo

1Skills CLI (Vercel)

npx skills add scenario-labs/skills --skill scenario-veo -a claude-code

2Manually: put the files in place

~/.claude/skills/scenario-veo/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/scenario-veo/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about scenario-veo

How do I install scenario-veo in Claude Code?

Run npx skills add scenario-labs/skills --skill scenario-veo -a claude-code. The skill file is saved at ~/.claude/skills/scenario-veo/SKILL.md.

What does scenario-veo do?

It helps generate or extend videos with Google Veo models through Scenario MCP. Supported workflows include text prompts, image references, frame transitions, and audio.

What does scenario-veo need to run?

It needs Scenario MCP and Veo models available in Scenario. Set generateAudio explicitly for each model.

Source text

SKILL.md · MIT
---
name: scenario-veo
description: "Use when generating or extending video with Google Veo models on Scenario via MCP: text-to-video, image-to-video from a first frame, first and last frame transitions, reference-to-video (R2V) with asset or style reference images, native audio with dialogue, sound effects, and ambience, negative prompts, seeded reruns, extending a 16:9 clip, or choosing a quality, fast, or lite tier. Keywords: Veo 3.1, Veo 3.1 Fast, Veo 3.1 Lite, Extend Video, Google, T2V, I2V, V2V, 720p, 1080p."
license: MIT
---

# Scenario Veo Video

## Overview

Veo, Google's video family on Scenario, ships four members at authoring time: Veo 3.1 (full quality,
reference images with a style switch), Veo 3.1 Fast (same modes, quicker, no switch), Veo 3.1 Lite
(frame anchors only, cheapest), and Veo 3.1 Extend Video (continues a clip). Discover them with
`search` and treat `model_schema_get` as the contract: members agree on parameter names and disagree
on which inputs exist at all.

Connection and the core loop: see the `scenario` skill in this repo; model-agnostic video work: the
`scenario-video` skill. If a sibling skill named here is missing from your available skills, load it
with `skill_get` (Scenario MCP) or ask the user to install it
(https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag
the gap.

## Quick reference

Mode follows from the inputs (names from the live schema):

| Mode        | Inputs                     | Behavior                                                  |
| ----------- | -------------------------- | --------------------------------------------------------- |
| Text        | `prompt`                   | `aspectRatio` 16:9 or 9:16                                |
| First frame | `image` (+ `prompt`)       | opens on that frame; a mismatched image may be cropped    |
| Transition  | `image` + `lastFrameImage` | bridges the stills; prompt one continuous move            |
| Reference   | `referenceImages` (1 to 3) | subject or style consistency; `duration` locked to 8      |
| Extend      | `video` (Extend member)    | continues the clip; 16:9 source, short side 720p or 1080p |

`image` and `referenceImages` are mutually exclusive. `referenceImagesType` exists on full Veo 3.1
alone and reads the whole array one way: `ASSET` (default) carries subjects, objects, and scenes;
`STYLE` carries palette, lighting, and texture. Fast takes references without the switch; Lite takes
none. Shared across the three generators at authoring time: `negativePrompt`, `resolution` (`720p`,
`1080p`), `duration` (4, 6, or 8 seconds), and `seed`. `generateAudio` is required on every member
and moves the price. The Extend member takes only `prompt`, `video`, `generateAudio`, and `seed`: no
duration, resolution, or ratio controls. At authoring time price spanned roughly five times between
Lite and full 3.1 for one image-to-video job, and one extension cost more than a fresh full
generation, so aim for the shot in one 8 second pass and `dry_run` the same payload on two members
before a batch.

## The soundstage is in the prompt

With `generateAudio: true`, Veo renders synchronized dialogue, effects, and ambience, and it takes
audio direction literally. Put spoken lines in quotation marks, prefix effects with `SFX:` and room
tone with `Ambient noise:`. A prompt with no audio direction still gets a soundtrack, just not the
one you meant. When a clip needs silence for later scoring, set `generateAudio: false` rather than
prompting for quiet.

## Prompt one continuous shot

Write present-tense prose ordered as cinematography, subject, action, context, style: camera and
shot scale first, one primary arc, roughly 90 to 250 words. For several beats in one clip, timestamp
lines work (`[00:00-00:02] Medium shot...`), spans fitting inside the chosen duration.

## Worked example: a dialogue shot from character references

1. `search` with `target="models"`, `query="veo"`, `public=true`. Prefer the newest non-deprecated
   hits, e.g. `model_veo3-1` and `model_veo3-1-fast` (live hits at authoring time: re-discover each
   session).
2. `model_schema_get` on the chosen id: confirm which reference inputs exist before writing the
   payload.
3. `upload_asset` two character stills (see the `scenario` skill) to get asset ids.
4. `model_run` with that `model_id`, `dry_run=true`, and
   `parameters={"prompt": "Medium shot, the knight lowers her visor and says, \"Hold the line.\" Torchlight flickers on wet stone. Ambient noise: distant thunder. SFX: metal visor clank.", "referenceImages": ["asset_a", "asset_b"], "referenceImagesType": "ASSET", "duration": 8, "resolution": "1080p", "aspectRatio": "16:9", "generateAudio": true}`.
   Estimate the same job on the Fast id (drop `referenceImagesType`, absent there) and compare.
5. Repeat `model_run` with `wait=false`, then `jobs_wait` with the returned job id, re-called with
   `pending_job_ids` on timeout, never a second `model_run`.
6. `asset_display` the output and review with sound. To iterate on wording alone, hold an explicit
   `seed` fixed across reruns.

## Common mistakes

- Combining `image` with `referenceImages`: mutually exclusive; pick the opening state or
  consistency.
- Any duration but 8 with `referenceImages`: reference mode supports only 8 seconds.
- Sending `referenceImages` to Lite or `referenceImagesType` to Fast: the schema decides which
  inputs exist.
- Omitting `generateAudio`: it is required on every member; pass it explicitly.
- Extending a 9:16 clip: Extend takes 16:9 sources with a 720p or 1080p short side only.
- Writing the prompt as a list of negatives: describe the wanted scene, reserve `negativePrompt` for
  what to discourage.

© scenario-labs · MIT · scenario-labs/skills

Similar skills

All skills for AI and ML →

From the same set172

The whole set →
scenario-caption-studio scenario-caption-studio — a skill that runs Scenario captioning over MCP: transcribe a clip, burn in styled captions, export an SRT sidecar, translate the words. CX Codex +1 861installs scenario-kling scenario-kling is a Claude Code skill for generating and editing Kling videos through Scenario MCP, including text or image prompts, motion transfer, lipsync, and prompt-guided edits. CX Codex +1 859installs scenario-workflows scenario-workflows drives the agent through running a saved Scenario graph over MCP: list, read the input contract, price it with a dry run, then start the job. CX Codex +1 858installs scenario-workflow-authoring scenario-workflow-authoring is a Claude Code skill that builds and edits Scenario workflow graphs via MCP, including migration from Weavy or ComfyUI. CX Codex +1 854installs scenario-ideogram scenario-ideogram is a Claude Code skill for generating and editing images via Ideogram on Scenario, including designs with readable text, background removal, and editable layers. CX Codex +1 848installs scenario-grok-imagine-image scenario-grok-imagine-image guides image generation and reference-based editing with xAI's Grok Imagine family on Scenario via MCP. Excels at rendering sharp in-image copy. CX Codex +1 847installs scenario-minimax-music scenario-minimax-music controls MiniMax Music 3.0 and Cover models on Scenario via MCP. It builds songs with vocals from lyric sheets or restyles audio files while preserving melodies. CX Codex +1 847installs scenario-gemini-omni The scenario-gemini-omni skill for Claude Code generates, extends, and edits video with Gemini Omni models via Scenario MCP, using text, a first frame, or reference images for subject consistency. CX Codex +1 845installs

Project sponsors

Companies that keep this analytics open