- Home
- Skills
- Game Development
- animclip
More screenshots
Works with the AI Agents you already use
animclip
Turn text topics into 9:16 pixel-art animated shorts with synced TTS, 8-bit music, and automated scene layout.
Free
animclip
Example session with this skill installed
/animclip A 10-second intro clip that shows off what this skill does: "this whole clip was made by AI"
- Read your context and instructions
- Compiled the animclip
Here's the script I wrote for your clip. 4 scenes, ~9.5s, 130 bpm, free edge-tts voice (en-US-AndrewNeural), paper-collage theme.
| # | Line | Look |
|---|---|---|
| 1 | "This whole clip was made by AI" | tee outfit, wave pose, drops in, yellow burst · headline This clip / made by AI |
| 2 | "The script, the art, even the sound" | hoodie outfit typing · bulb pops on "script", chip on "sound" · typing SFX |
| 3 | "So what did I do? I typed one sentence" | lab coat, shrug → point on "typed" · question mark on "do" · paper-rip transition |
| 4 | "[excited] And here's the result" | cheer + hop, shake/flash/burst, star + fire icons, power-up SFX · headline pretty wild |
{
"id": "hello_en",
"voice": {"engine": "edge", "name": "en-US-AndrewNeural", "rate": "+10%"},
"scenes": [
{"say": "This whole clip was made by AI", "bg": "kraft", "transition": "cut",
"char": {"outfit": "tee", "pose": "wave", "enter": "drop"},
"headline": ["This clip", "made by AI"], "fx": ["burst"]},
{"say": "The script, the art, even the sound", "bg": "grid", "transition": "slide",
"char": {"outfit": "hoodie", "pose": "type", "enter": "slide_left", "x": 0.42},
"icons": [{"name": "bulb", "x": 0.78, "y": 0.42, "on": "script"}, {"name": "chip", "x": 0.8, "y": 0.62, "on": "sound"}],
"headline": ["script", "art", "sound"], "sfx": [{"name": "typing", "at": 0.2}]}
]
}
(scenes 3-4 trimmed here; the full file ships as examples/hello.json)
Then I ran the build
$ python scripts/build.py hello.json
[animclip] 4 scenes, 9.5s @ 130bpm, props -> remotion/public/jobs/hello_en/props.json
VIDEO: ~/Videos/animclip/hello_en.mp4
Output: ~/Videos/animclip/hello_en.mp4 — 1080×1920, 24fps (motion at 12fps), word-synced captions, 8-bit music ducked under the voice, scene cuts snapped to the beat. The screenshots on this page are frames from this exact render.
Next steps
- Want a different voice? Swap in any edge-tts voice, or set
ELEVENLABS_API_KEYand use"engine": "elevenlabs"for emotion tags like[excited]. - Need real screenshots in a scene? Add a
shotand I'll give you a shot list to fill in. - Happy with it? I can stretch it into a 30-60s version with a hook and CTA.
Connects securely to your tools. The creator never sees your data.
About this skill
Turn any topic into a production-ready vertical short for social media without touching a video editor. This skill automates the entire creative pipeline from scriptwriting to final mp4 rendering using a distinct pixel-art and paper-collage aesthetic.
What it does
- Automated scriptwriting generates punchy 30 to 60 second scripts with hooks, CTAs, and emotive TTS tags.
- Dynamic scene layout handles character positioning, safe-zone management for TikTok/Reels, and asset randomization.
- Audio synthesis integrates ElevenLabs or edge-tts with per-word timing and generated 8-bit background music.
- Visual asset generation creates sprite sheets for characters, outfits, and icons on the fly using Python.
- Programmatic rendering uses Remotion to compile scenes, transitions, and synced SFX into 1080x1920 mp4 files.
How it works
- Initialize assets by running the sprite and SFX synthesis scripts to build your local library.
- Generate the script using the
/animclipcommand to create a structuredscript.jsonfile. - Handle screenshots by reviewing the auto-generated shot list for any real-world UI or brand captures needed.
- Preview and render using the build script to inspect stills before committing to the full video render.
Frameworks & tools
Python 3.10+, Node.js 18+, FFmpeg, Remotion, ElevenLabs API, and edge-tts.
Why this beats prompting it yourself
Generic prompts often fail to sync audio with visual cues or respect mobile safe zones. This skill uses a precise JSON schema to lock timing to the beat and ensures high-quality stop-motion visuals that standard video LLMs cannot yet replicate with consistency.
Use cases
- Create engaging product comparisons or feature reviews with real screenshots.
- Turn educational facts into viral 8-bit animated shorts.
- Generate quick social media reactions or news bites with branded assets.
- Automate faceless YouTube Shorts or TikTok content at scale.
Known limitations
Requires an internet connection at render time to fetch Google Fonts. Screen recordings as icons are not supported and must be converted to static frames.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Game Development.
Requires Python 3.10+, Node.js, and FFmpeg. Rendering requires an internet connection for fonts. No support for direct video-file icons.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
- Software
Python
Node.jsFFmpeg on PATH
- Optional
ElevenLabs
First run: cd remotion && npm install, then pip install edge-tts numpy scipy pillow requests. Rendering needs internet (Google Fonts). Brand logo list ships empty - add your own.