design-image-studio
Turn a loose brief into design-quality AI images: posters, product shots, PPT art, infographics, with real art direction instead of generic AI art.
- What
- Turn a loose brief into design-quality AI images: posters, product shots, PPT art, infographics, with real art direction instead of generic AI art.
- Cost
- Free
- Needs
- Use "design-image-studio" with a coding agent that has shell access (e.g. Claude Code).
- Install
- Copy the installer prompt below into your Muse β your agent does the rest.
π³ Paid API required. Curated by Skill Harbor: this skill turns a loose creative brief into design-quality AI images instead of generic AI art. It keeps a full design-system prompt as the reasoning layer (purpose, audience, channel, visual system, hierarchy, anti-filler and anti-slop rules), compiles it into a compact brief, then into the shortest useful image prompt. It routes each request to a task workflow (poster, product, PPT, infographic, teaching diagram), ships a Python wrapper (scripts/design_image.py) that generates directly via Volcengine's Seedream models, and offers a prompt-only mode that just prints the design reasoning, the compiled brief, and the final prompt. By @kangarooking, listed here with credit to its creator. Discovered via github.com/topics/ai-skills. Honest caveats: generation needs a Volcengine API key, a paid image-generation service billed per image; image models still struggle with dense, tiny text, and the skill itself warns against pixel-accurate UI recreation or precise text rendering; the repo includes a few Chinese examples. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseCommunity-built. Skill Harbor doesn't audit code β review the source before installing.
Use "design-image-studio" with a coding agent that has shell access (e.g. Claude Code). Prerequisites: Python 3, a Volcengine API key (paid image-generation service; generation is billed per image, draft settings cost less than final quality). 1. Fetch the repo: https://github.com/kangarooking/design-image-studio, then copy SKILL.md, the scripts/ folder, and the references/ folder into a temporary folder. 2. Safety check: read SKILL.md and scripts/design_image.py for anything suspicious (unexpected network calls, credential harvesting). API keys go in environment variables only, never in the code or the chat. STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md, scripts/ and references/ into the agent's skills directory, in a folder named "design-image-studio". 4. Set your Volcengine API key as an environment variable on your machine (never paste it into the chat); tell me which variable name the script expects. 5. Test cheaply first: run scripts/design_image.py with --prompt-only on a sample brief to see the design reasoning, the compiled brief, and the final prompt. Then run a real generation at draft quality before any final-quality rerun. 6. Verify with no network calls: frontmatter valid, files in place, script shows its help text. 7. Report what was installed, where, and what I still need to do myself (e.g. saving my API key). Tip: use --prompt-only mode when you only want the art direction and the prompt, no image. Avoid asking for pixel-accurate UI or dense tiny text; the skill itself says those fail. Safety: this skill calls a paid API on your behalf. Keep your key in an environment variable or the secure vault, never in chat, and review each generation command before it runs.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you β no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the sellerβs own page, usually Stripe.
What does the β next to a creatorβs name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself β always check a build before installing it.