teamday-ai/agents/animate-avatar

Animate Avatar Skill

Generate animated videos from static avatar images for use in apps, websites, or social profiles.

Overview

This skill automates the process of:

1. Generating multiple video animations from a static avatar image
2. Optimizing videos for web delivery

Activity Philosophy

Default Generation: Create 3 videos per avatar:

• 2 Work activities - Shows the character being productive
• 1 Relax activity - Shows the character taking a break

This 2:1 ratio of work-to-relax creates variety and humanizes characters.

Work Activity Prompts (pick 2)

• "Character typing on a computer keyboard"
• "Character writing or signing documents"
• "Character giving a presentation with gestures"
• "Character thinking deeply, tapping chin"
• "Character nodding while listening attentively"
• "Character examining something closely"
• "Character taking notes with a pen"

Relax Activity Prompts (pick 1)

• "Character drinking coffee or tea"
• "Character playing a small guitar"
• "Character eating a snack happily"
• "Character stretching and yawning"
• "Character listening to music, bobbing head"
• "Character waving hello cheerfully"

Models & Pricing

Prerequisites

• FAL AI API key set as FAL_KEY environment variable
• ffmpeg installed for video optimization

Usage

bun .claude/skills/animate-avatar/scripts/animate-avatar.ts \
  --avatar "avatar-name" \
  --prompts "Character typing on keyboard,Character signing a document,Character drinking coffee"

Parameters

Output

Videos are:

1. Generated via FAL AI (~70s each)
2. Optimized with ffmpeg (320x320, ~150-250KB)
3. Saved to the output directory

Tips for Best Results

Good Prompts

• Keep motions subtle - loops better
• Match the character's personality
• Work: typing, writing, presenting, thinking
• Relax: drinking, stretching, waving

Avoid

• Large movements that break the loop
• "Walking", "running", "jumping" - too dynamic
• Complex multi-step actions

Video Specifications