# AI avatar video storyboard

A skill based on a story on Agent Stories.

Writes a storyboard from a fixed template that keeps wardrobe, setting and lighting the same in every clip prompt.

Task: Marketing
Works with: Claude, ChatGPT, Gemini, Any AI chat
Tools: Google Flow
Difficulty: Intermediate
Country: Singapore

Use this when you want a short AI avatar video and need every clip to look consistent.
Skip this if you need the clips made for you, or you will not disclose the AI avatar where the platform or client expects it.

Credit: From the story of Gavin Sim. A Singapore AI educator makes short videos with an AI avatar of himself instead of a shoot day with a crew
Source: https://agentstories.org/stories/gavin-sim-singapore-ai-avatar-videos.html

## Skill text

Please turn the text below into a reusable skill. If you are Claude, save it as a skill. If you are ChatGPT or Gemini, save it as the instructions for a Project, custom GPT or Gem. If you cannot save skills, just follow these instructions now.

Name: AI avatar video storyboard

Description: Use this when I want a short AI avatar video and need every clip to look consistent.

Ask me for:
1. Video length, topic and audience.
2. My fixed template: wardrobe, setting, lighting, camera (static or slow push in), and whether my avatar speaks.

Steps:
1. Plan 4 to 6 scenes.
2. For each scene give the line I say, what is on screen and the exact prompt for that clip.
3. Repeat the same wardrobe, setting and lighting in every clip prompt.
4. Flag any scene that might break consistency.

Output:
1. A scene table with Line, On screen and Clip prompt.
2. A list of consistency risks.

Rules: When I report a new way a clip broke, add a rule to the template. Remind me to disclose the AI avatar where the platform or client expects it.

## More

- [This skill as a web page](https://agentstories.org/skills/avatar-video-storyboard.html)
- [All skills, as a Markdown list](https://agentstories.org/skills.md)
- [Skills directory](https://agentstories.org/skills/)
