- Home
- Skills
- Workflow Automation
- reels-html
Works with the AI Agents you already use
Reels Html
Make 9:16 vertical app-demo videos (Reels, Stories, TikTok, Shorts) from an HTML scene, with voice-over and captions.
$5
reels-html
Example session with this skill installed
Make a 10-second vertical demo video about the reels-html tool, using the included demo scene. Narrate it in Brazilian Portuguese with a female voice.
- Read your context and instructions
- Compiled the reels-html
Summary
The skill turned the included demo scene into a 9:16 MP4 with a Brazilian Portuguese voice-over and synced captions. Output: 1080x1920, 30 fps, 11.5 seconds, H.264 video and AAC audio, 0.9 MB.
Steps and output
| Step | Command | Output |
|---|---|---|
| Voice-over | python locucao.py demo | audio/demo.wav, 10.4 s |
| Caption timing | python pausas.py demo | caption timings for each line of narration |
| Frame capture | node gravar.js demo | 305 frames (11.5 s) in gravacoes/demo/ |
| Assembly | python montar.py demo | mp4/demo.mp4 |
Deliverable
The file mp4/demo.mp4, with the voice-over and captions. The phone screens in the demo scene are illustrative and are not a real app.
Next steps
Replace the demo scene with your own app screens, edit the narration in reels.json, and run the four commands again from your project folder.
Connects securely to your tools. The creator never sees your data.
About this skill
Turns an app or system into a short vertical demo video (9:16, 1080x1920). The skill builds an animated phone mockup with taps, typing, and screen changes, adds a title, a synced caption and voice-over (free edge-tts or Google TTS), and ends with a brand closing card. Scenes are plain HTML and CSS, rendered frame by frame in Chrome and joined with FFmpeg. Use it for product demos, "how it works" clips, and short ads. It does not edit real footage and does not make horizontal video.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
No support for real-world footage or 16:9 layouts. Requires Python 3.10+ and Node 18+. Online assets (fonts/icons) require internet during recording.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Software
Python
Permissions
Network (all documented in SKILL.md): texttospeech.googleapis.com + www.googleapis.com/auth/cloud-platform (OAuth scope) only if voice provider is google; Edge TTS via edge-tts package (default voice); fonts.googleapis.com and cdn.jsdelivr.net load fonts/icons while recording. Nothing is sent to the author. Terminal: only ffmpeg with fixed args. Env vars: REELS_NAVEGADOR (chrome/msedge), GOOGLE_CLOUD_PROJECT / GOOGLE_APPLICATION_CREDENTIALS (google provider only). Files: writes frames to the user's gravacoes/ folder.