Automated summary
Generates animated videos from static avatar images using FAL AI models like Kling, LTX, or Veo, with a default 2:1 ratio of work to relax activities.
Strengths
- Automates video generation and optimization
- Multiple AI model options for quality/cost trade-offs
- Produces web-optimized small MP4 files (~150-250 KB)
Limitations
- Requires a FAL AI API key
- Limited to subtle motions for looping
- Videos are short (5 seconds) and low resolution (320x320)
Use when you need simple, looping character animations for web profiles, apps, or social media.
Do not use for complex storytelling, high-resolution video needs, or when API dependencies are undesirable.
Security analysis
SafeThe skill uses Bash to run a TypeScript script that calls the FAL AI API for video generation. It does not execute any dangerous commands, exfiltrate data, or disable safety features. The use of ffmpeg is for legitimate video optimization.
No concerns found
How this analysis is madeExamples
Generate 3 animated videos from my avatar image showing typing, writing, and drinking coffee.Create a looping animation of my avatar waving hello using the Kling model.I need two work animations and one relax animation from this static avatar, using Veo for highest quality.name: animate-avatar description: Generate animated videos from static avatar images using FAL AI. Create looping work and relax animations with Kling V2.6 Pro, LTX, or Veo models. allowed-tools: Bash, Read, Write env:
- FAL_KEY
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:
- Generating multiple video animations from a static avatar image
- 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
| Model | Flag | Cost | Notes |
|-------|------|------|-------|
| Kling V2.6 Pro | --model kling | $0.07/sec ($0.35/5s video) | Default, best quality/cost |
| LTX-2-19B | --model ltx | ~$0.20/video | Cheaper for small res |
| Veo 3.1 | --model veo | $0.20/sec ($1.00/5s video) | Highest quality |
Prerequisites
- FAL AI API key set as
FAL_KEYenvironment 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
| Parameter | Required | Default | Description |
|-----------|----------|---------|-------------|
| --avatar | Yes | - | Avatar name or path to image |
| --count | No | 3 | Number of videos to generate |
| --prompts | No | Auto | Comma-separated motion prompts |
| --model | No | kling | Model: kling, ltx, or veo |
| --skip-optimize | No | false | Skip ffmpeg optimization |
Output
Videos are:
- Generated via FAL AI (~70s each)
- Optimized with ffmpeg (320x320, ~150-250KB)
- 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
| Property | Value | |----------|-------| | Resolution | 320x320 | | Format | MP4 (H.264) | | Duration | 5 seconds | | Target Size | ~150-250 KB |
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/animate-avatar-mryiqgnv/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/animate-avatar-mryiqgnv' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/animate-avatar-mryiqgnv/download' --output '.skill-downloads/animate-avatar-mryiqgnv/SKILL.md.part' && mv '.skill-downloads/animate-avatar-mryiqgnv/SKILL.md.part' '.skill-downloads/animate-avatar-mryiqgnv/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash, Read, Write
Original excerpt: Prerequisites
- FAL AI API key set as
FAL_KEYenvironment variable - ffmpeg installed for video optimization
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/animate-avatar-mryiqgnv/SKILL.md' && test -s '.skill-downloads/animate-avatar-mryiqgnv/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/animate-avatar' && cp -R '.skill-downloads/animate-avatar-mryiqgnv' '.claude/skills/animate-avatar'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/animate-avatar-mryiqgnv'openskills read 'animate-avatar-mryiqgnv'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/animate-avatar-mryiqgnv/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Writing Fragments
Content
Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.
UI Copywriting & Auditing
Content
Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.
Music MIDI Extraction
Content
Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.