- Home
- Skills
- Agents & Orchestration
- ghibli comic
More screenshots
Works with the AI Agents you already use
ghibli comic
Generate Studio Ghibli-style covers and multi-panel comics from text topics with WeChat upload support.
Free
ghibli comic
Example session with this skill installed
Create a 4-panel Ghibli-style comic about a developer working late at night in a cozy workshop, then stitch it into a long image.
- Read your context and instructions
- Compiled the ghibli comic
- Generated the image
I have generated a 4-panel Ghibli-style comic based on the theme "developer working late in a workshop." The storyboard was planned using gemini-3.0-flash, and images were rendered using gemini-3.0-pro. The panels have been stitched into a single vertical long-form image.
Ghibli Comic: The Midnight Workshop
| File | Description |
|---|---|
00-workshop-long.jpg | Stitched vertical comic (4 panels) |
storyboard.json | LLM-generated scene descriptions and character notes |
pages/01-ghibli.jpg | Panel 1: Establishing shot of the workshop at dusk |
pages/02-ghibli.jpg | Panel 2: Close-up of coffee steam and glowing monitor |
pages/03-ghibli.jpg | Panel 3: Developer focused on code, warm lantern light |
pages/04-ghibli.jpg | Panel 4: Morning sun hitting the desk, project complete |
Next steps
- Review the
storyboard.jsonto see the prompts used for each panel. - Run with
--uploadto push the final long image to your WeChat media library. - If character details shift between Panel 2 and 3, re-run with a more specific
--topicdescribing the character's clothing.
00-workshop-long.jpg
PNG · 1536×1024
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Creating visually consistent illustrations for WeChat Official Accounts or personal blogs is time-consuming and often requires expensive designers. This skill automates the generation of Studio Ghibli-inspired covers and multi-panel comics directly from your topics or articles using Gemini models.
What it does
- Ghibli-Style Generation transforms any text topic or Markdown article into high-quality Miyazaki-inspired artwork.
- Multi-Panel Comics handles storyboarding, per-page generation, and vertical stitching for long-form visual storytelling.
- Visual Consistency maintains character and style continuity across multiple panels using reference images and character notes.
- Auto-Layout Management supports various grid styles including four-panel, cinematic wide-shots, and mixed reaction-shot layouts.
- WeChat Integration uploads results directly to the WeChat media platform and returns the
thumb_media_idfor immediate use.
How it works
- Trigger the skill by providing a topic or a path to a Markdown article.
- Select Mode between
coverfor single 2.35:1 banners orcomicfor multi-page narratives. - Review Storyboard in
dry-runmode to check LLM-generated prompts before consuming image generation credits. - Execute the Python script to generate images, perform post-processing (cropping/stitching), and optionally upload to WeChat.
Frameworks & tools
Built with Python and Node.js (for Gemini web reverse API). It utilizes gemini-3.0-pro for image generation and gemini-3.0-flash for narrative planning.
Why this beats prompting it yourself
Writing prompts that prevent AI from adding gibberish text or watermarks is difficult. This skill includes hardcoded negative constraints, handles complex multi-step consistency across panels, and automates the tedious cropping and stitching work required for specific social media formats.
Use cases
- Article Covers generate 2.35:1 banners for WeChat Official Account headers.
- Visual Storytelling convert product launch logs or personal stories into multi-page vertical comics.
- Social Media Assets create Ghibli-themed avatars or background illustrations for portfolios.
- Rapid Prototyping quickly visualize storyboards for video or animation projects.
Known limitations
Reverse API cookies expire frequently and require manual re-authentication via a browser. Character consistency across long comics is high but not 100% perfect. No support for text overlays within the images.
Requires manual Chrome login for reverse API. Character consistency may vary slightly between panels. No text/watermark support. 2.35:1 aspect ratio involves post-generation cropping.
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 any payment.
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
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts