Create a coherent branded carousel with seven card layouts, three visual styles and portrait, square and wide exports. Includes actual PNG renders, editable SVGs, reusable brand/content JSON and measured text-fit evidence. Original Skillrove tools.
Three authored practice briefs · actual exports · local editing and generation
index.htmlportrait-01.png + .svg (six cards)square-01.png + .svg (six cards)wide-01.png + .svg (six cards)carousel.jsonlayout-evidence.jsonhandoff.mddelivery-manifest.jsonLocal editor + delivery ZIPDesigners and creators making coherent educational or launch carousels.
Non-ASCII text needs a licensed font with the required glyphs; overflow stops rendering.
Capabilities: 3–10 original cards using cover, statement, list, comparison, steps, sourced metric and closing layouts. Folio, outline and contrast styles combine supplied brand colors with measured typography. Export portrait 1080×1440, square 1080×1080 and wide 1200×675 in one run. Choose a local licensed font for non-ASCII text; missing glyphs and unreadable overflow stop the render.
Deliverables: full-resolution PNGs, editable text-based SVGs, responsive keyboard gallery, reusable carousel.json, measured layout evidence, publishing handoff and SHA-256 manifest. Font files are never embedded or redistributed.
Requirements and run: Python 3.10+ and Pillow 11.3–12.x. Create a virtual environment, install requirements.txt, then python scripts/build-carousel.py --input examples/carousel.json --output ./sample-carousel. Optional --font points to a local TTF/TTC (face index 0).
Validation: real Skillrove copy rendered six cards in all three formats. Independent runs exercised all seven layouts, three styles, local Latin/Chinese fonts, XML validity, missing ASCII glyphs, measured text regions, actual outline-border clearance, tab expansion, gallery controls and mobile layout.
Limits: PNG preserves the measured font; editable SVG needs a matching local font for identical geometry. Supplied metric text is not an independently calculated result. Review content, target-platform crops and visual hierarchy before publishing. No image-generation API, social upload or scheduling service is called.
Version 1.0.0: original MIT-licensed renderer and instructions, with source-method attribution. Individual purchase and eligible active membership unlock the package.
FROM PACKAGE TO FIRST RESULT
Bring your own brief, ask your agent to prepare the input, then edit and generate actual files in the bundled local studio.
A complete launch carousel, ready to review and edit.
Use Brand Carousel Studio at .agents/skills/brand-carousel-studio. Read SKILL.md. Create a six-card launch carousel for Northstar, a fictional project-planning app. Audience: independent design studios. Explain the workflow from a clear brief to a reviewed handoff. Use a bold editorial direction, concise copy, and portrait, square and wide formats. Avoid invented performance numbers. Ask for essential missing facts, preserve unknowns, and prepare a reviewed input. Check dependencies, generate into a new folder, inspect the actual files and explain any failed checks. You may open the bundled local studio for editing. Do not publish or purchase external services.Copy this request to your agent after installing the package. The local studio runs on your computer; the public preview is an example, not a hosted generation service.
These steps use a project folder. Open the project in your agent and run terminal commands from its root.
Package folder .agents/skills/brand-carousel-studio
Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.
Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.
Ask your agent to check the package dependencies, then launch the editor. Change the fields, generate real files, and download the complete delivery ZIP. Every run keeps previous results.
cd .agents/skills/brand-carousel-studio
python3 -m venv .venv
.venv/bin/python -m pip install -r requirements.txt
.venv/bin/python scripts/start-studio.py --output ./my-carousel-studioRead SKILL.md, review the generator and check its runtime requirements before running:
cd .agents/skills/brand-carousel-studio
python3 -m venv .venv
.venv/bin/python -m pip install -r requirements.txt
.venv/bin/python scripts/build-carousel.py --input examples/carousel.json --output ./sample-carouselSwitch Portrait, Square and Wide, open full-resolution PNGs, inspect all six cards and compare measured text regions with the artwork. Edit brand colors/content/style and regenerate into a fresh directory. SVG remains editable.
Python 3.10+ and Pillow. For Chinese pass a licensed local font; TTC uses face index 0. PNG is the measured render. SVG needs a matching font; font files are not embedded. No social upload or image-generation service.
If sample-carousel already exists, change the output to ./sample-carousel-2. Existing files are never overwritten.
Use Brand Carousel Studio at .agents/skills/brand-carousel-studio. Read SKILL.md and review scripts/build-carousel.py. Run examples/carousel.json into a new output folder and show me all generated files. Keep fictional sample content clearly labeled.
Tried this workflow? Help others decide with an honest review.
The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.
This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.
The documented 1.1.0 workflow lists: index.html; portrait-01.png + .svg (six cards); square-01.png + .svg (six cards); wide-01.png + .svg (six cards); carousel.json; layout-evidence.json; handoff.md; delivery-manifest.json; Local editor + delivery ZIP. Some files or exports are optional; follow the package’s setup and inspect the delivered result.
Python 3.10+ and Pillow. For Chinese pass a licensed local font; TTC uses face index 0. PNG is the measured render. SVG needs a matching font; font files are not embedded. No social upload or image-generation service.
