BeyondArtist plugin
A design skill for freelancers and creators: designer and artist roles, phone-size feed tests and upload-ready delivery files.
- 68 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill reads video links and category pages and writes design files and local memory, uploading nothing.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/beyondartistDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill reads video links and category pages and writes design files and local memory, uploading nothing.
This is third-party code. Review the repository files before installing.
What it does
BeyondArtist puts two roles between your request and the image. The designer finds the message, audience and what the whole category repeats. The artist turns that into something unexpected, and both approve the actual pixels. Work follows nine steps: understand, classify and retrieve, research the category and Pinterest, design the idea, hand off and deliver. The `/beyondartist:autopilot` command takes a YouTube link: the skill reads the title, description, chapters and current thumbnail, produces three concepts, tests each among competitor thumbnails at phone and desktop sizes and returns an upload-ready file, a master and editable HTML. Design memory is stored locally in `~/.beyondartist/memory`, with no API key or vector database.
Who it is for. Freelancers, content creators and marketers who need thumbnails, carousels and posters without design training.
Good fit when
- A video needs a thumbnail that survives phone-size previews.
- A social carousel must explain a service in short copy with warmth.
- Output must stand out from the flood of template AI images.
- Exact text, contrast and element collisions need checking before delivery.
Not a fit when
- You need an image generation service: the skill works through your agent and model, see `docs/no-image-model.md`.
- You need a promised click-through gain; the author states the skill promises none.
- You want people or characters from the gallery; examples fall under a separate `ASSET-LICENSE.md`.
Example request
Use BeyondArtist: make a carousel about my service for small business owners, short copy, warm humor.Limitations
The skill never uploads anything and never promises clicks: the check measures the file, not the future. It runs locally on Python. Gallery examples do not become your defaults and their terms are in `ASSET-LICENSE.md`. Install routes for other agents are in `docs/getting-started.md`. Installation in Codex, ChatGPT, Gemini and Hermes follows separate routes in `docs/getting-started.md`, and some features depend on the environment. Faces and characters from the gallery fall under `ASSET-LICENSE.md`. Category research relies on public pages, so results depend on source availability.
How to disable. Remove the plugin with `/plugin uninstall beyondartist@beyondartist` and delete `~/.beyondartist/memory` if you want saved preferences erased.
FAQ
How do I install BeyondArtist in Claude Code?
Run `/plugin marketplace add beyondtahir/beyondartist`, then `/plugin install beyondartist@beyondartist` and restart Claude Code.
Do I need an image model?
No, there is a no-image-model mode described in `docs/no-image-model.md`. The skill sets exact text in real fonts itself.
What does Autopilot do?
It takes a link and, with no brief, produces three concepts, tests them among competitor thumbnails and prepares delivery files. It publishes nothing itself.
Where is memory stored?
Personal preferences and projects stay local in `~/.beyondartist/memory`, outside the skill. Shared design memory holds records, studies and references.
Which platforms does it fit?
The skill makes thumbnails, carousels, posters and character art, accounting for platform and format. Size and contrast are checked at phone, desktop and sidebar sizes.
Discussion
No questions or reviews yet.
Related
PluginsA skill that writes prompts for video, image and music generation on 14 platforms and can submit them in the browser
A skill that makes video in pure code: narrated explainers and website promos in 35 visual styles, in 16:9 and 9:16.
A skill that makes promo videos from code: direction, in-browser animation with motion blur, its own score and a 60 fps MP4
A skill for Claude Code and Codex that builds app launch films from HTML, music and voiceover and renders them on your machine.
Skill that turns a photo into an original 3:4 art poster: scene analysis, a fitting medium, palette and typography
A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.
README in short
A plugin with an autopilot command, an example gallery and docs on the process and automation. Install in Claude Code takes two commands, and Codex, ChatGPT, Gemini and Hermes each have instructions.